{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"gpuType": "T4"
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
},
"accelerator": "GPU",
"widgets": {
"application/vnd.jupyter.widget-state+json": {
"8ff8c13284c14676b06e4745721752ff": {
"model_module": "@jupyter-widgets/controls",
"model_name": "VBoxModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "VBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "VBoxView",
"box_style": "",
"children": [
"IPY_MODEL_16c9ddf0f69f48a08f2ba7b0767c6e04",
"IPY_MODEL_15902149c92341eb96bde04388332f92",
"IPY_MODEL_ef37ebf8ddfa4a54aa6e6ff22a80e1ff",
"IPY_MODEL_589a3dee05d14f978c816c5e160e3c6d"
],
"layout": "IPY_MODEL_c0ae0beb39ca47d38ce6c970aaa1b61e"
}
},
"0f76ed54c37841919f69e3177fd6d7ec": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_2bc31dd7c1de48d987ef760bf2d15147",
"placeholder": "",
"style": "IPY_MODEL_12e0ce2415404baaaff00fea8d956d54",
"value": "
Copy a token from your Hugging Face\ntokens page and paste it below.
Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file. "
}
},
"e4cf51a9ec524655885fa9d07495fb38": {
"model_module": "@jupyter-widgets/controls",
"model_name": "PasswordModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "PasswordModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "PasswordView",
"continuous_update": true,
"description": "Token:",
"description_tooltip": null,
"disabled": false,
"layout": "IPY_MODEL_39949b8863224db28a986fe21017325c",
"placeholder": "",
"style": "IPY_MODEL_aa046de0210e4c449ba575e1c36bacb1",
"value": ""
}
},
"767318ed9ad944be8f48ad555be1e1ff": {
"model_module": "@jupyter-widgets/controls",
"model_name": "CheckboxModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "CheckboxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "CheckboxView",
"description": "Add token as git credential?",
"description_tooltip": null,
"disabled": false,
"indent": true,
"layout": "IPY_MODEL_9955e32bd5ae46268f8d9722622d174e",
"style": "IPY_MODEL_25b7d7c4c9e84d10b9965d53a63546c0",
"value": true
}
},
"bc645f00ff0f43cf859068ea57352721": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ButtonModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "ButtonModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "ButtonView",
"button_style": "",
"description": "Login",
"disabled": false,
"icon": "",
"layout": "IPY_MODEL_cff0d261124249a68f95b38739010ca5",
"style": "IPY_MODEL_1839eb1041f546ea8d52cb0d6f8c4c8a",
"tooltip": ""
}
},
"3e660dd6ce074fd8bdf4a8244dd8b7a9": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HTMLModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_b96787f8562c4dbc9d56ddcf52a32712",
"placeholder": "",
"style": "IPY_MODEL_e1ba30e7cf0546329471a3f6f5e0b4bc",
"value": "\nPro Tip: If you don't already have one, you can create a dedicated\n'notebooks' token with 'write' access, that you can then easily reuse for all\nnotebooks. "
}
},
"c0ae0beb39ca47d38ce6c970aaa1b61e": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": "center",
"align_self": null,
"border": null,
"bottom": null,
"display": "flex",
"flex": null,
"flex_flow": "column",
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": "50%"
}
},
"2bc31dd7c1de48d987ef760bf2d15147": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"12e0ce2415404baaaff00fea8d956d54": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"39949b8863224db28a986fe21017325c": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"aa046de0210e4c449ba575e1c36bacb1": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"9955e32bd5ae46268f8d9722622d174e": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"25b7d7c4c9e84d10b9965d53a63546c0": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"cff0d261124249a68f95b38739010ca5": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"1839eb1041f546ea8d52cb0d6f8c4c8a": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ButtonStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "ButtonStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"button_color": null,
"font_weight": ""
}
},
"b96787f8562c4dbc9d56ddcf52a32712": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"e1ba30e7cf0546329471a3f6f5e0b4bc": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"27216c11c3594a509ba423dd639459b5": {
"model_module": "@jupyter-widgets/controls",
"model_name": "LabelModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "LabelModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "LabelView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_a78a804660594c2abf59eca6eca50572",
"placeholder": "",
"style": "IPY_MODEL_ef36b661ee3c4502a5cbe5f7766f154d",
"value": "Connecting..."
}
},
"a78a804660594c2abf59eca6eca50572": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"ef36b661ee3c4502a5cbe5f7766f154d": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"16c9ddf0f69f48a08f2ba7b0767c6e04": {
"model_module": "@jupyter-widgets/controls",
"model_name": "LabelModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "LabelModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "LabelView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_8097ed945e114ed5b87a4972d6f0d859",
"placeholder": "",
"style": "IPY_MODEL_0f5dccb7a8b44ac79b70340cbc5db798",
"value": "Token is valid (permission: write)."
}
},
"15902149c92341eb96bde04388332f92": {
"model_module": "@jupyter-widgets/controls",
"model_name": "LabelModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "LabelModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "LabelView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_8cd6e4522ef44d69b8b723af315e7237",
"placeholder": "",
"style": "IPY_MODEL_1cf3cc18ec1a4fb99655a5fc01bd1b22",
"value": "Your token has been saved in your configured git credential helpers (store)."
}
},
"ef37ebf8ddfa4a54aa6e6ff22a80e1ff": {
"model_module": "@jupyter-widgets/controls",
"model_name": "LabelModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "LabelModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "LabelView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_86587e674adc46748f3246f6db7bd632",
"placeholder": "",
"style": "IPY_MODEL_ba7dea34ec104c019006105901393e76",
"value": "Your token has been saved to /root/.cache/huggingface/token"
}
},
"589a3dee05d14f978c816c5e160e3c6d": {
"model_module": "@jupyter-widgets/controls",
"model_name": "LabelModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "LabelModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "LabelView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_821d176ebe3a4bf5afcc2fe8a731a242",
"placeholder": "",
"style": "IPY_MODEL_d0c0c8758616405786ab2144705b72c8",
"value": "Login successful"
}
},
"8097ed945e114ed5b87a4972d6f0d859": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"0f5dccb7a8b44ac79b70340cbc5db798": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"8cd6e4522ef44d69b8b723af315e7237": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"1cf3cc18ec1a4fb99655a5fc01bd1b22": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"86587e674adc46748f3246f6db7bd632": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"ba7dea34ec104c019006105901393e76": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"821d176ebe3a4bf5afcc2fe8a731a242": {
"model_module": "@jupyter-widgets/base",
"model_name": "LayoutModel",
"model_module_version": "1.2.0",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"d0c0c8758616405786ab2144705b72c8": {
"model_module": "@jupyter-widgets/controls",
"model_name": "DescriptionStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
}
}
}
},
"cells": [
{
"cell_type": "markdown",
"source": [
"Creating Virtual Display"
],
"metadata": {
"id": "GjMLnpMo_SVm"
}
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"id": "TEWKJ84cm6FR"
},
"outputs": [],
"source": [
"%%capture\n",
"!apt install python-opengl\n",
"!apt install ffmpeg\n",
"!apt install xvfb\n",
"!pip3 install pyvirtualdisplay"
]
},
{
"cell_type": "code",
"source": [
"# Virtual display\n",
"from pyvirtualdisplay import Display\n",
"\n",
"virtual_display = Display(visible=0, size=(1500, 1000))\n",
"virtual_display.start()"
],
"metadata": {
"id": "fG9T5VcqnRhm",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
},
"outputId": "bda3fb7b-5b16-44d9-8f9d-dc3f0be7caec"
},
"execution_count": 2,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
""
]
},
"metadata": {},
"execution_count": 2
}
]
},
{
"cell_type": "markdown",
"source": [
"Installing Dependencies"
],
"metadata": {
"id": "UArEHR-e_aGL"
}
},
{
"cell_type": "code",
"source": [
"!pip install stable-baselines3[extra]\n",
"!pip install gymnasium\n",
"!pip install huggingface_sb3\n",
"!pip install huggingface_hub\n",
"!pip install panda_gym"
],
"metadata": {
"id": "NnfPNIZlnU6f",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
},
"outputId": "58039115-eeb8-413e-c7b8-c7d4bd5ed0f1"
},
"execution_count": 3,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Requirement already satisfied: stable-baselines3[extra] in /usr/local/lib/python3.10/dist-packages (2.3.2)\n",
"Requirement already satisfied: gymnasium<0.30,>=0.28.1 in /usr/local/lib/python3.10/dist-packages (from stable-baselines3[extra]) (0.29.1)\n",
"Requirement already satisfied: numpy>=1.20 in /usr/local/lib/python3.10/dist-packages (from stable-baselines3[extra]) (1.25.2)\n",
"Requirement already satisfied: torch>=1.13 in /usr/local/lib/python3.10/dist-packages (from stable-baselines3[extra]) (2.3.0+cu121)\n",
"Requirement already satisfied: cloudpickle in /usr/local/lib/python3.10/dist-packages (from stable-baselines3[extra]) (2.2.1)\n",
"Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from stable-baselines3[extra]) (2.0.3)\n",
"Requirement already satisfied: matplotlib in /usr/local/lib/python3.10/dist-packages (from stable-baselines3[extra]) (3.7.1)\n",
"Requirement already satisfied: opencv-python in /usr/local/lib/python3.10/dist-packages (from stable-baselines3[extra]) (4.8.0.76)\n",
"Requirement already satisfied: pygame in /usr/local/lib/python3.10/dist-packages (from stable-baselines3[extra]) (2.5.2)\n",
"Requirement already satisfied: tensorboard>=2.9.1 in /usr/local/lib/python3.10/dist-packages (from stable-baselines3[extra]) (2.15.2)\n",
"Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from stable-baselines3[extra]) (5.9.5)\n",
"Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from stable-baselines3[extra]) (4.66.4)\n",
"Requirement already satisfied: rich in /usr/local/lib/python3.10/dist-packages (from stable-baselines3[extra]) (13.7.1)\n",
"Requirement already satisfied: shimmy[atari]~=1.3.0 in /usr/local/lib/python3.10/dist-packages (from stable-baselines3[extra]) (1.3.0)\n",
"Requirement already satisfied: pillow in /usr/local/lib/python3.10/dist-packages (from stable-baselines3[extra]) (9.4.0)\n",
"Requirement already satisfied: autorom[accept-rom-license]~=0.6.1 in /usr/local/lib/python3.10/dist-packages (from stable-baselines3[extra]) (0.6.1)\n",
"Requirement already satisfied: click in /usr/local/lib/python3.10/dist-packages (from autorom[accept-rom-license]~=0.6.1->stable-baselines3[extra]) (8.1.7)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from autorom[accept-rom-license]~=0.6.1->stable-baselines3[extra]) (2.31.0)\n",
"Requirement already satisfied: AutoROM.accept-rom-license in /usr/local/lib/python3.10/dist-packages (from autorom[accept-rom-license]~=0.6.1->stable-baselines3[extra]) (0.6.1)\n",
"Requirement already satisfied: typing-extensions>=4.3.0 in /usr/local/lib/python3.10/dist-packages (from gymnasium<0.30,>=0.28.1->stable-baselines3[extra]) (4.12.1)\n",
"Requirement already satisfied: farama-notifications>=0.0.1 in /usr/local/lib/python3.10/dist-packages (from gymnasium<0.30,>=0.28.1->stable-baselines3[extra]) (0.0.4)\n",
"Requirement already satisfied: ale-py~=0.8.1 in /usr/local/lib/python3.10/dist-packages (from shimmy[atari]~=1.3.0->stable-baselines3[extra]) (0.8.1)\n",
"Requirement already satisfied: absl-py>=0.4 in /usr/local/lib/python3.10/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]) (1.4.0)\n",
"Requirement already satisfied: grpcio>=1.48.2 in /usr/local/lib/python3.10/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]) (1.64.1)\n",
"Requirement already satisfied: google-auth<3,>=1.6.3 in /usr/local/lib/python3.10/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]) (2.27.0)\n",
"Requirement already satisfied: google-auth-oauthlib<2,>=0.5 in /usr/local/lib/python3.10/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]) (1.2.0)\n",
"Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.10/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]) (3.6)\n",
"Requirement already satisfied: protobuf!=4.24.0,>=3.19.6 in /usr/local/lib/python3.10/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]) (3.20.3)\n",
"Requirement already satisfied: setuptools>=41.0.0 in /usr/local/lib/python3.10/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]) (67.7.2)\n",
"Requirement already satisfied: six>1.9 in /usr/local/lib/python3.10/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]) (1.16.0)\n",
"Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]) (0.7.2)\n",
"Requirement already satisfied: werkzeug>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from tensorboard>=2.9.1->stable-baselines3[extra]) (3.0.3)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch>=1.13->stable-baselines3[extra]) (3.14.0)\n",
"Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.13->stable-baselines3[extra]) (1.12.1)\n",
"Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.13->stable-baselines3[extra]) (3.3)\n",
"Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.13->stable-baselines3[extra]) (3.1.4)\n",
"Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch>=1.13->stable-baselines3[extra]) (2023.6.0)\n",
"Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.13->stable-baselines3[extra]) (12.1.105)\n",
"Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.13->stable-baselines3[extra]) (12.1.105)\n",
"Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.13->stable-baselines3[extra]) (12.1.105)\n",
"Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /usr/local/lib/python3.10/dist-packages (from torch>=1.13->stable-baselines3[extra]) (8.9.2.26)\n",
"Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /usr/local/lib/python3.10/dist-packages (from torch>=1.13->stable-baselines3[extra]) (12.1.3.1)\n",
"Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /usr/local/lib/python3.10/dist-packages (from torch>=1.13->stable-baselines3[extra]) (11.0.2.54)\n",
"Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /usr/local/lib/python3.10/dist-packages (from torch>=1.13->stable-baselines3[extra]) (10.3.2.106)\n",
"Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /usr/local/lib/python3.10/dist-packages (from torch>=1.13->stable-baselines3[extra]) (11.4.5.107)\n",
"Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /usr/local/lib/python3.10/dist-packages (from torch>=1.13->stable-baselines3[extra]) (12.1.0.106)\n",
"Requirement already satisfied: nvidia-nccl-cu12==2.20.5 in /usr/local/lib/python3.10/dist-packages (from torch>=1.13->stable-baselines3[extra]) (2.20.5)\n",
"Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch>=1.13->stable-baselines3[extra]) (12.1.105)\n",
"Requirement already satisfied: triton==2.3.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.13->stable-baselines3[extra]) (2.3.0)\n",
"Requirement already satisfied: nvidia-nvjitlink-cu12 in /usr/local/lib/python3.10/dist-packages (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.13->stable-baselines3[extra]) (12.5.40)\n",
"Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->stable-baselines3[extra]) (1.2.1)\n",
"Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib->stable-baselines3[extra]) (0.12.1)\n",
"Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->stable-baselines3[extra]) (4.53.0)\n",
"Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->stable-baselines3[extra]) (1.4.5)\n",
"Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib->stable-baselines3[extra]) (24.0)\n",
"Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib->stable-baselines3[extra]) (3.1.2)\n",
"Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.10/dist-packages (from matplotlib->stable-baselines3[extra]) (2.8.2)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->stable-baselines3[extra]) (2023.4)\n",
"Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas->stable-baselines3[extra]) (2024.1)\n",
"Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich->stable-baselines3[extra]) (3.0.0)\n",
"Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/dist-packages (from rich->stable-baselines3[extra]) (2.16.1)\n",
"Requirement already satisfied: importlib-resources in /usr/local/lib/python3.10/dist-packages (from ale-py~=0.8.1->shimmy[atari]~=1.3.0->stable-baselines3[extra]) (6.4.0)\n",
"Requirement already satisfied: cachetools<6.0,>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from google-auth<3,>=1.6.3->tensorboard>=2.9.1->stable-baselines3[extra]) (5.3.3)\n",
"Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.10/dist-packages (from google-auth<3,>=1.6.3->tensorboard>=2.9.1->stable-baselines3[extra]) (0.4.0)\n",
"Requirement already satisfied: rsa<5,>=3.1.4 in /usr/local/lib/python3.10/dist-packages (from google-auth<3,>=1.6.3->tensorboard>=2.9.1->stable-baselines3[extra]) (4.9)\n",
"Requirement already satisfied: requests-oauthlib>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from google-auth-oauthlib<2,>=0.5->tensorboard>=2.9.1->stable-baselines3[extra]) (1.3.1)\n",
"Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich->stable-baselines3[extra]) (0.1.2)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->autorom[accept-rom-license]~=0.6.1->stable-baselines3[extra]) (3.3.2)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->autorom[accept-rom-license]~=0.6.1->stable-baselines3[extra]) (3.7)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->autorom[accept-rom-license]~=0.6.1->stable-baselines3[extra]) (2.0.7)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->autorom[accept-rom-license]~=0.6.1->stable-baselines3[extra]) (2024.6.2)\n",
"Requirement already satisfied: MarkupSafe>=2.1.1 in /usr/local/lib/python3.10/dist-packages (from werkzeug>=1.0.1->tensorboard>=2.9.1->stable-baselines3[extra]) (2.1.5)\n",
"Requirement already satisfied: mpmath<1.4.0,>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.13->stable-baselines3[extra]) (1.3.0)\n",
"Requirement already satisfied: pyasn1<0.7.0,>=0.4.6 in /usr/local/lib/python3.10/dist-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard>=2.9.1->stable-baselines3[extra]) (0.6.0)\n",
"Requirement already satisfied: oauthlib>=3.0.0 in /usr/local/lib/python3.10/dist-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<2,>=0.5->tensorboard>=2.9.1->stable-baselines3[extra]) (3.2.2)\n",
"Requirement already satisfied: gymnasium in /usr/local/lib/python3.10/dist-packages (0.29.1)\n",
"Requirement already satisfied: numpy>=1.21.0 in /usr/local/lib/python3.10/dist-packages (from gymnasium) (1.25.2)\n",
"Requirement already satisfied: cloudpickle>=1.2.0 in /usr/local/lib/python3.10/dist-packages (from gymnasium) (2.2.1)\n",
"Requirement already satisfied: typing-extensions>=4.3.0 in /usr/local/lib/python3.10/dist-packages (from gymnasium) (4.12.1)\n",
"Requirement already satisfied: farama-notifications>=0.0.1 in /usr/local/lib/python3.10/dist-packages (from gymnasium) (0.0.4)\n",
"Requirement already satisfied: huggingface_sb3 in /usr/local/lib/python3.10/dist-packages (3.0)\n",
"Requirement already satisfied: huggingface-hub~=0.8 in /usr/local/lib/python3.10/dist-packages (from huggingface_sb3) (0.23.2)\n",
"Requirement already satisfied: pyyaml~=6.0 in /usr/local/lib/python3.10/dist-packages (from huggingface_sb3) (6.0.1)\n",
"Requirement already satisfied: wasabi in /usr/local/lib/python3.10/dist-packages (from huggingface_sb3) (1.1.3)\n",
"Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from huggingface_sb3) (1.25.2)\n",
"Requirement already satisfied: cloudpickle>=1.6 in /usr/local/lib/python3.10/dist-packages (from huggingface_sb3) (2.2.1)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface-hub~=0.8->huggingface_sb3) (3.14.0)\n",
"Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub~=0.8->huggingface_sb3) (2023.6.0)\n",
"Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub~=0.8->huggingface_sb3) (24.0)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface-hub~=0.8->huggingface_sb3) (2.31.0)\n",
"Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub~=0.8->huggingface_sb3) (4.66.4)\n",
"Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub~=0.8->huggingface_sb3) (4.12.1)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub~=0.8->huggingface_sb3) (3.3.2)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub~=0.8->huggingface_sb3) (3.7)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub~=0.8->huggingface_sb3) (2.0.7)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub~=0.8->huggingface_sb3) (2024.6.2)\n",
"Requirement already satisfied: huggingface_hub in /usr/local/lib/python3.10/dist-packages (0.23.2)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (3.14.0)\n",
"Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (2023.6.0)\n",
"Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (24.0)\n",
"Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (6.0.1)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (2.31.0)\n",
"Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (4.66.4)\n",
"Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (4.12.1)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (3.3.2)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (3.7)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (2.0.7)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (2024.6.2)\n",
"Requirement already satisfied: panda_gym in /usr/local/lib/python3.10/dist-packages (3.0.7)\n",
"Requirement already satisfied: gymnasium>=0.26 in /usr/local/lib/python3.10/dist-packages (from panda_gym) (0.29.1)\n",
"Requirement already satisfied: pybullet in /usr/local/lib/python3.10/dist-packages (from panda_gym) (3.2.6)\n",
"Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from panda_gym) (1.25.2)\n",
"Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from panda_gym) (1.11.4)\n",
"Requirement already satisfied: cloudpickle>=1.2.0 in /usr/local/lib/python3.10/dist-packages (from gymnasium>=0.26->panda_gym) (2.2.1)\n",
"Requirement already satisfied: typing-extensions>=4.3.0 in /usr/local/lib/python3.10/dist-packages (from gymnasium>=0.26->panda_gym) (4.12.1)\n",
"Requirement already satisfied: farama-notifications>=0.0.1 in /usr/local/lib/python3.10/dist-packages (from gymnasium>=0.26->panda_gym) (0.0.4)\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"Importing the Packages"
],
"metadata": {
"id": "5q0Nsqyd_i9W"
}
},
{
"cell_type": "code",
"source": [
"import os\n",
"\n",
"import gymnasium as gym\n",
"import panda_gym\n",
"\n",
"from huggingface_sb3 import load_from_hub, package_to_hub\n",
"\n",
"from stable_baselines3 import A2C\n",
"from stable_baselines3.common.evaluation import evaluate_policy\n",
"from stable_baselines3.common.vec_env import DummyVecEnv, VecNormalize\n",
"from stable_baselines3.common.env_util import make_vec_env\n",
"\n",
"from huggingface_hub import notebook_login"
],
"metadata": {
"id": "Cf9zRbU_nXfU"
},
"execution_count": 4,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"Creating the Environment"
],
"metadata": {
"id": "ozogIGuHAJ5n"
}
},
{
"cell_type": "code",
"source": [
"env_id = \"PandaReachDense-v3\"\n",
"\n",
"# Create the env\n",
"env = gym.make(env_id)\n",
"\n",
"# Get the state space and action space\n",
"s_size = env.observation_space.shape\n",
"a_size = env.action_space"
],
"metadata": {
"id": "V0ZQQtgLna7C",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
},
"outputId": "dd8c8642-f232-48d7-a074-2ebd98e7afe1"
},
"execution_count": 5,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"/usr/local/lib/python3.10/dist-packages/ipykernel/ipkernel.py:283: DeprecationWarning: `should_run_async` will not call `transform_cell` automatically in the future. Please pass the result to `transformed_cell` argument and any exception that happen during thetransform in `preprocessing_exc_tuple` in IPython 7.17 and above.\n",
" and should_run_async(code)\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"Observation Space"
],
"metadata": {
"id": "5riYZ7gXAPb7"
}
},
{
"cell_type": "code",
"source": [
"print(\"_____OBSERVATION SPACE_____ \\n\")\n",
"print(\"The State Space is: \", s_size)\n",
"print(\"Sample observation\", env.observation_space.sample()) # Get a random observation"
],
"metadata": {
"id": "QBrnZ01PnjZB",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
},
"outputId": "89dc28d4-04e8-4397-c7cc-01c9e37a3ef0"
},
"execution_count": 6,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"_____OBSERVATION SPACE_____ \n",
"\n",
"The State Space is: None\n",
"Sample observation OrderedDict([('achieved_goal', array([ 0.78458875, -6.220511 , -9.073549 ], dtype=float32)), ('desired_goal', array([-5.211849 , 2.830356 , -7.8033385], dtype=float32)), ('observation', array([ 1.9924148, -8.279003 , -4.5922694, 7.5727925, -2.136467 ,\n",
" -2.6619885], dtype=float32))])\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"Action Space"
],
"metadata": {
"id": "0h1UIHAHAUUM"
}
},
{
"cell_type": "code",
"source": [
"print(\"\\n _____ACTION SPACE_____ \\n\")\n",
"print(\"The Action Space is: \", a_size)\n",
"print(\"Action Space Sample\", env.action_space.sample()) # Take a random action"
],
"metadata": {
"id": "rWFWF-lInlnz",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
},
"outputId": "a16d3d0c-b376-4e15-a598-3f8d49e45126"
},
"execution_count": 7,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\n",
" _____ACTION SPACE_____ \n",
"\n",
"The Action Space is: Box(-1.0, 1.0, (3,), float32)\n",
"Action Space Sample [-0.07075059 -0.86420137 0.85553956]\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"Adding a wrapper to normalise rewards"
],
"metadata": {
"id": "PoGKpbjuAd5n"
}
},
{
"cell_type": "code",
"source": [
"env = make_vec_env(env_id, n_envs=4)\n",
"\n",
"env = VecNormalize(env, norm_obs=True, norm_reward=True, clip_obs=10.)"
],
"metadata": {
"id": "QrdbSEpcnmY5"
},
"execution_count": 8,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"Creating the A2C model"
],
"metadata": {
"id": "uKPfx4awAskD"
}
},
{
"cell_type": "code",
"source": [
"model = A2C(policy = \"MultiInputPolicy\",\n",
" env = env,\n",
" verbose=1)"
],
"metadata": {
"id": "qANbDpzVnpnG",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
},
"outputId": "10a05cce-7e1d-45a9-9e14-2ade3240d6bd"
},
"execution_count": 9,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Using cpu device\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"Training the A2C agent for 1000000 timesteps"
],
"metadata": {
"id": "qlcfoqYuAxuH"
}
},
{
"cell_type": "code",
"source": [
"model.learn(1_000_000)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
},
"id": "jzrg6nkKrWsQ",
"outputId": "616cd991-7b25-4bbc-a958-9a74499a3688"
},
"execution_count": 10,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"/usr/local/lib/python3.10/dist-packages/ipykernel/ipkernel.py:283: DeprecationWarning: `should_run_async` will not call `transform_cell` automatically in the future. Please pass the result to `transformed_cell` argument and any exception that happen during thetransform in `preprocessing_exc_tuple` in IPython 7.17 and above.\n",
" and should_run_async(code)\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001b[1;30;43mStreaming output truncated to the last 5000 lines.\u001b[0m\n",
"| std | 0.302 |\n",
"| value_loss | 0.000388 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.75 |\n",
"| ep_rew_mean | -0.221 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 23800 |\n",
"| time_elapsed | 1560 |\n",
"| total_timesteps | 476000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.604 |\n",
"| explained_variance | 0.924 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 23799 |\n",
"| policy_loss | 0.00592 |\n",
"| std | 0.3 |\n",
"| value_loss | 0.000387 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.7 |\n",
"| ep_rew_mean | -0.201 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 304 |\n",
"| iterations | 23900 |\n",
"| time_elapsed | 1567 |\n",
"| total_timesteps | 478000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.587 |\n",
"| explained_variance | 0.973 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 23899 |\n",
"| policy_loss | 0.00627 |\n",
"| std | 0.299 |\n",
"| value_loss | 0.00013 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.61 |\n",
"| ep_rew_mean | -0.2 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 24000 |\n",
"| time_elapsed | 1573 |\n",
"| total_timesteps | 480000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.564 |\n",
"| explained_variance | 0.982 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 23999 |\n",
"| policy_loss | 0.0053 |\n",
"| std | 0.297 |\n",
"| value_loss | 0.000114 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.75 |\n",
"| ep_rew_mean | -0.215 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 24100 |\n",
"| time_elapsed | 1580 |\n",
"| total_timesteps | 482000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.575 |\n",
"| explained_variance | 0.967 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 24099 |\n",
"| policy_loss | -0.00196 |\n",
"| std | 0.298 |\n",
"| value_loss | 0.00024 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.69 |\n",
"| ep_rew_mean | -0.208 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 24200 |\n",
"| time_elapsed | 1586 |\n",
"| total_timesteps | 484000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.569 |\n",
"| explained_variance | 0.983 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 24199 |\n",
"| policy_loss | 0.0031 |\n",
"| std | 0.298 |\n",
"| value_loss | 0.000154 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.85 |\n",
"| ep_rew_mean | -0.222 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 24300 |\n",
"| time_elapsed | 1593 |\n",
"| total_timesteps | 486000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.558 |\n",
"| explained_variance | 0.964 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 24299 |\n",
"| policy_loss | 0.000412 |\n",
"| std | 0.296 |\n",
"| value_loss | 0.000434 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.68 |\n",
"| ep_rew_mean | -0.201 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 24400 |\n",
"| time_elapsed | 1599 |\n",
"| total_timesteps | 488000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.555 |\n",
"| explained_variance | 0.973 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 24399 |\n",
"| policy_loss | 0.00264 |\n",
"| std | 0.296 |\n",
"| value_loss | 0.000104 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.79 |\n",
"| ep_rew_mean | -0.219 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 304 |\n",
"| iterations | 24500 |\n",
"| time_elapsed | 1607 |\n",
"| total_timesteps | 490000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.535 |\n",
"| explained_variance | 0.975 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 24499 |\n",
"| policy_loss | -0.00366 |\n",
"| std | 0.294 |\n",
"| value_loss | 0.000205 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.95 |\n",
"| ep_rew_mean | -0.235 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 24600 |\n",
"| time_elapsed | 1613 |\n",
"| total_timesteps | 492000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.522 |\n",
"| explained_variance | 0.978 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 24599 |\n",
"| policy_loss | -0.00626 |\n",
"| std | 0.293 |\n",
"| value_loss | 0.000141 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.65 |\n",
"| ep_rew_mean | -0.208 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 24700 |\n",
"| time_elapsed | 1619 |\n",
"| total_timesteps | 494000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.511 |\n",
"| explained_variance | 0.913 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 24699 |\n",
"| policy_loss | -0.0108 |\n",
"| std | 0.291 |\n",
"| value_loss | 0.000323 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.68 |\n",
"| ep_rew_mean | -0.2 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 24800 |\n",
"| time_elapsed | 1625 |\n",
"| total_timesteps | 496000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.518 |\n",
"| explained_variance | 0.956 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 24799 |\n",
"| policy_loss | 0.000693 |\n",
"| std | 0.293 |\n",
"| value_loss | 0.000156 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.8 |\n",
"| ep_rew_mean | -0.212 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 24900 |\n",
"| time_elapsed | 1632 |\n",
"| total_timesteps | 498000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.51 |\n",
"| explained_variance | 0.925 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 24899 |\n",
"| policy_loss | -0.00333 |\n",
"| std | 0.292 |\n",
"| value_loss | 0.000244 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.75 |\n",
"| ep_rew_mean | -0.209 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 25000 |\n",
"| time_elapsed | 1638 |\n",
"| total_timesteps | 500000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.498 |\n",
"| explained_variance | 0.955 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 24999 |\n",
"| policy_loss | 0.000141 |\n",
"| std | 0.291 |\n",
"| value_loss | 0.000232 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.72 |\n",
"| ep_rew_mean | -0.204 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 25100 |\n",
"| time_elapsed | 1644 |\n",
"| total_timesteps | 502000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.498 |\n",
"| explained_variance | 0.97 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 25099 |\n",
"| policy_loss | 0.0171 |\n",
"| std | 0.291 |\n",
"| value_loss | 0.000277 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.88 |\n",
"| ep_rew_mean | -0.227 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 25200 |\n",
"| time_elapsed | 1651 |\n",
"| total_timesteps | 504000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.474 |\n",
"| explained_variance | 0.928 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 25199 |\n",
"| policy_loss | 0.00339 |\n",
"| std | 0.289 |\n",
"| value_loss | 0.000273 |\n",
"------------------------------------\n",
"-------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.64 |\n",
"| ep_rew_mean | -0.205 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 25300 |\n",
"| time_elapsed | 1657 |\n",
"| total_timesteps | 506000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.47 |\n",
"| explained_variance | 0.971 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 25299 |\n",
"| policy_loss | -0.000358 |\n",
"| std | 0.288 |\n",
"| value_loss | 0.000236 |\n",
"-------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.72 |\n",
"| ep_rew_mean | -0.214 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 25400 |\n",
"| time_elapsed | 1664 |\n",
"| total_timesteps | 508000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.481 |\n",
"| explained_variance | 0.987 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 25399 |\n",
"| policy_loss | 0.000577 |\n",
"| std | 0.289 |\n",
"| value_loss | 7.3e-05 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.96 |\n",
"| ep_rew_mean | -0.246 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 25500 |\n",
"| time_elapsed | 1670 |\n",
"| total_timesteps | 510000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.477 |\n",
"| explained_variance | 0.991 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 25499 |\n",
"| policy_loss | 0.00195 |\n",
"| std | 0.289 |\n",
"| value_loss | 8.5e-05 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.66 |\n",
"| ep_rew_mean | -0.212 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 25600 |\n",
"| time_elapsed | 1678 |\n",
"| total_timesteps | 512000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.469 |\n",
"| explained_variance | 0.987 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 25599 |\n",
"| policy_loss | -0.00508 |\n",
"| std | 0.288 |\n",
"| value_loss | 0.000106 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.65 |\n",
"| ep_rew_mean | -0.203 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 25700 |\n",
"| time_elapsed | 1683 |\n",
"| total_timesteps | 514000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.459 |\n",
"| explained_variance | 0.958 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 25699 |\n",
"| policy_loss | -0.0039 |\n",
"| std | 0.287 |\n",
"| value_loss | 0.000203 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.78 |\n",
"| ep_rew_mean | -0.225 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 25800 |\n",
"| time_elapsed | 1690 |\n",
"| total_timesteps | 516000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.459 |\n",
"| explained_variance | 0.943 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 25799 |\n",
"| policy_loss | 0.0142 |\n",
"| std | 0.288 |\n",
"| value_loss | 0.000381 |\n",
"------------------------------------\n",
"-------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.75 |\n",
"| ep_rew_mean | -0.206 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 25900 |\n",
"| time_elapsed | 1696 |\n",
"| total_timesteps | 518000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.454 |\n",
"| explained_variance | 0.912 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 25899 |\n",
"| policy_loss | -0.000539 |\n",
"| std | 0.287 |\n",
"| value_loss | 0.00023 |\n",
"-------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.79 |\n",
"| ep_rew_mean | -0.221 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 26000 |\n",
"| time_elapsed | 1703 |\n",
"| total_timesteps | 520000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.436 |\n",
"| explained_variance | 0.971 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 25999 |\n",
"| policy_loss | 0.00105 |\n",
"| std | 0.286 |\n",
"| value_loss | 0.00014 |\n",
"------------------------------------\n",
"-------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.74 |\n",
"| ep_rew_mean | -0.212 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 26100 |\n",
"| time_elapsed | 1709 |\n",
"| total_timesteps | 522000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.436 |\n",
"| explained_variance | 0.995 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 26099 |\n",
"| policy_loss | -0.000882 |\n",
"| std | 0.286 |\n",
"| value_loss | 2.71e-05 |\n",
"-------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.76 |\n",
"| ep_rew_mean | -0.217 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 26200 |\n",
"| time_elapsed | 1716 |\n",
"| total_timesteps | 524000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.419 |\n",
"| explained_variance | 0.907 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 26199 |\n",
"| policy_loss | 0.00117 |\n",
"| std | 0.284 |\n",
"| value_loss | 0.000584 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.71 |\n",
"| ep_rew_mean | -0.203 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 26300 |\n",
"| time_elapsed | 1722 |\n",
"| total_timesteps | 526000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.408 |\n",
"| explained_variance | 0.925 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 26299 |\n",
"| policy_loss | -0.00444 |\n",
"| std | 0.283 |\n",
"| value_loss | 0.000139 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.66 |\n",
"| ep_rew_mean | -0.205 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 26400 |\n",
"| time_elapsed | 1729 |\n",
"| total_timesteps | 528000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.425 |\n",
"| explained_variance | 0.981 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 26399 |\n",
"| policy_loss | 0.00431 |\n",
"| std | 0.285 |\n",
"| value_loss | 0.000151 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.72 |\n",
"| ep_rew_mean | -0.215 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 26500 |\n",
"| time_elapsed | 1735 |\n",
"| total_timesteps | 530000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.415 |\n",
"| explained_variance | 0.965 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 26499 |\n",
"| policy_loss | -0.00216 |\n",
"| std | 0.284 |\n",
"| value_loss | 0.000151 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.75 |\n",
"| ep_rew_mean | -0.211 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 26600 |\n",
"| time_elapsed | 1742 |\n",
"| total_timesteps | 532000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.382 |\n",
"| explained_variance | 0.965 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 26599 |\n",
"| policy_loss | 0.0106 |\n",
"| std | 0.281 |\n",
"| value_loss | 0.000305 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.69 |\n",
"| ep_rew_mean | -0.209 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 26700 |\n",
"| time_elapsed | 1748 |\n",
"| total_timesteps | 534000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.379 |\n",
"| explained_variance | 0.882 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 26699 |\n",
"| policy_loss | 0.00592 |\n",
"| std | 0.281 |\n",
"| value_loss | 0.000727 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.79 |\n",
"| ep_rew_mean | -0.228 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 26800 |\n",
"| time_elapsed | 1754 |\n",
"| total_timesteps | 536000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.373 |\n",
"| explained_variance | 0.981 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 26799 |\n",
"| policy_loss | 0.0091 |\n",
"| std | 0.28 |\n",
"| value_loss | 0.000249 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.58 |\n",
"| ep_rew_mean | -0.196 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 26900 |\n",
"| time_elapsed | 1761 |\n",
"| total_timesteps | 538000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.349 |\n",
"| explained_variance | 0.973 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 26899 |\n",
"| policy_loss | 0.0015 |\n",
"| std | 0.279 |\n",
"| value_loss | 9.46e-05 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.7 |\n",
"| ep_rew_mean | -0.208 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 27000 |\n",
"| time_elapsed | 1767 |\n",
"| total_timesteps | 540000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.342 |\n",
"| explained_variance | 0.982 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 26999 |\n",
"| policy_loss | 0.00197 |\n",
"| std | 0.278 |\n",
"| value_loss | 9.57e-05 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.77 |\n",
"| ep_rew_mean | -0.211 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 27100 |\n",
"| time_elapsed | 1774 |\n",
"| total_timesteps | 542000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.324 |\n",
"| explained_variance | 0.808 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 27099 |\n",
"| policy_loss | -0.0056 |\n",
"| std | 0.277 |\n",
"| value_loss | 0.000701 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.83 |\n",
"| ep_rew_mean | -0.221 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 27200 |\n",
"| time_elapsed | 1780 |\n",
"| total_timesteps | 544000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.314 |\n",
"| explained_variance | 0.97 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 27199 |\n",
"| policy_loss | 0.000458 |\n",
"| std | 0.276 |\n",
"| value_loss | 0.000201 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.57 |\n",
"| ep_rew_mean | -0.203 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 27300 |\n",
"| time_elapsed | 1787 |\n",
"| total_timesteps | 546000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.315 |\n",
"| explained_variance | 0.985 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 27299 |\n",
"| policy_loss | -0.00777 |\n",
"| std | 0.276 |\n",
"| value_loss | 0.00015 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.67 |\n",
"| ep_rew_mean | -0.203 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 27400 |\n",
"| time_elapsed | 1793 |\n",
"| total_timesteps | 548000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.299 |\n",
"| explained_variance | 0.962 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 27399 |\n",
"| policy_loss | -0.00159 |\n",
"| std | 0.274 |\n",
"| value_loss | 0.00015 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.85 |\n",
"| ep_rew_mean | -0.229 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 27500 |\n",
"| time_elapsed | 1800 |\n",
"| total_timesteps | 550000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.277 |\n",
"| explained_variance | 0.986 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 27499 |\n",
"| policy_loss | -0.00298 |\n",
"| std | 0.272 |\n",
"| value_loss | 0.000202 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.73 |\n",
"| ep_rew_mean | -0.216 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 27600 |\n",
"| time_elapsed | 1806 |\n",
"| total_timesteps | 552000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.26 |\n",
"| explained_variance | 0.984 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 27599 |\n",
"| policy_loss | 0.00736 |\n",
"| std | 0.271 |\n",
"| value_loss | 0.000391 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.66 |\n",
"| ep_rew_mean | -0.207 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 27700 |\n",
"| time_elapsed | 1813 |\n",
"| total_timesteps | 554000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.271 |\n",
"| explained_variance | 0.923 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 27699 |\n",
"| policy_loss | 0.00112 |\n",
"| std | 0.272 |\n",
"| value_loss | 0.000314 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.65 |\n",
"| ep_rew_mean | -0.199 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 27800 |\n",
"| time_elapsed | 1819 |\n",
"| total_timesteps | 556000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.27 |\n",
"| explained_variance | 0.743 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 27799 |\n",
"| policy_loss | -0.0071 |\n",
"| std | 0.272 |\n",
"| value_loss | 0.00126 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.7 |\n",
"| ep_rew_mean | -0.207 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 27900 |\n",
"| time_elapsed | 1825 |\n",
"| total_timesteps | 558000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.253 |\n",
"| explained_variance | 0.984 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 27899 |\n",
"| policy_loss | -0.00463 |\n",
"| std | 0.27 |\n",
"| value_loss | 9.94e-05 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.72 |\n",
"| ep_rew_mean | -0.217 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 28000 |\n",
"| time_elapsed | 1831 |\n",
"| total_timesteps | 560000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.254 |\n",
"| explained_variance | 0.923 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 27999 |\n",
"| policy_loss | 0.00141 |\n",
"| std | 0.27 |\n",
"| value_loss | 0.000601 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.74 |\n",
"| ep_rew_mean | -0.209 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 28100 |\n",
"| time_elapsed | 1838 |\n",
"| total_timesteps | 562000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.22 |\n",
"| explained_variance | 0.969 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 28099 |\n",
"| policy_loss | 0.000165 |\n",
"| std | 0.267 |\n",
"| value_loss | 0.000164 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.78 |\n",
"| ep_rew_mean | -0.223 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 28200 |\n",
"| time_elapsed | 1844 |\n",
"| total_timesteps | 564000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.205 |\n",
"| explained_variance | 0.991 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 28199 |\n",
"| policy_loss | -0.00123 |\n",
"| std | 0.266 |\n",
"| value_loss | 0.000105 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.61 |\n",
"| ep_rew_mean | -0.196 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 28300 |\n",
"| time_elapsed | 1851 |\n",
"| total_timesteps | 566000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.203 |\n",
"| explained_variance | 0.978 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 28299 |\n",
"| policy_loss | 0.00347 |\n",
"| std | 0.266 |\n",
"| value_loss | 8.82e-05 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.74 |\n",
"| ep_rew_mean | -0.213 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 28400 |\n",
"| time_elapsed | 1857 |\n",
"| total_timesteps | 568000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.18 |\n",
"| explained_variance | 0.985 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 28399 |\n",
"| policy_loss | -0.00355 |\n",
"| std | 0.264 |\n",
"| value_loss | 0.00012 |\n",
"------------------------------------\n",
"-------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.84 |\n",
"| ep_rew_mean | -0.226 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 28500 |\n",
"| time_elapsed | 1863 |\n",
"| total_timesteps | 570000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.172 |\n",
"| explained_variance | 0.97 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 28499 |\n",
"| policy_loss | -0.000405 |\n",
"| std | 0.263 |\n",
"| value_loss | 0.000287 |\n",
"-------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.77 |\n",
"| ep_rew_mean | -0.222 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 28600 |\n",
"| time_elapsed | 1869 |\n",
"| total_timesteps | 572000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.158 |\n",
"| explained_variance | 0.949 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 28599 |\n",
"| policy_loss | 0.00533 |\n",
"| std | 0.262 |\n",
"| value_loss | 0.000354 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.78 |\n",
"| ep_rew_mean | -0.213 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 28700 |\n",
"| time_elapsed | 1876 |\n",
"| total_timesteps | 574000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.146 |\n",
"| explained_variance | 0.968 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 28699 |\n",
"| policy_loss | 0.0017 |\n",
"| std | 0.261 |\n",
"| value_loss | 0.000186 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.64 |\n",
"| ep_rew_mean | -0.198 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 28800 |\n",
"| time_elapsed | 1884 |\n",
"| total_timesteps | 576000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.135 |\n",
"| explained_variance | 0.985 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 28799 |\n",
"| policy_loss | -0.00245 |\n",
"| std | 0.259 |\n",
"| value_loss | 0.000143 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.61 |\n",
"| ep_rew_mean | -0.2 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 28900 |\n",
"| time_elapsed | 1890 |\n",
"| total_timesteps | 578000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.109 |\n",
"| explained_variance | 0.97 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 28899 |\n",
"| policy_loss | 0.00246 |\n",
"| std | 0.258 |\n",
"| value_loss | 0.000181 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.79 |\n",
"| ep_rew_mean | -0.218 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 29000 |\n",
"| time_elapsed | 1897 |\n",
"| total_timesteps | 580000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.111 |\n",
"| explained_variance | 0.993 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 28999 |\n",
"| policy_loss | 0.00504 |\n",
"| std | 0.258 |\n",
"| value_loss | 6.2e-05 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.71 |\n",
"| ep_rew_mean | -0.215 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 29100 |\n",
"| time_elapsed | 1903 |\n",
"| total_timesteps | 582000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.105 |\n",
"| explained_variance | 0.978 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 29099 |\n",
"| policy_loss | -0.00418 |\n",
"| std | 0.257 |\n",
"| value_loss | 0.000143 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.57 |\n",
"| ep_rew_mean | -0.192 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 29200 |\n",
"| time_elapsed | 1910 |\n",
"| total_timesteps | 584000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.0944 |\n",
"| explained_variance | 0.956 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 29199 |\n",
"| policy_loss | 0.00571 |\n",
"| std | 0.257 |\n",
"| value_loss | 0.000137 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.83 |\n",
"| ep_rew_mean | -0.227 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 29300 |\n",
"| time_elapsed | 1916 |\n",
"| total_timesteps | 586000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.104 |\n",
"| explained_variance | 0.991 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 29299 |\n",
"| policy_loss | 0.000974 |\n",
"| std | 0.258 |\n",
"| value_loss | 0.000115 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.64 |\n",
"| ep_rew_mean | -0.206 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 29400 |\n",
"| time_elapsed | 1923 |\n",
"| total_timesteps | 588000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.083 |\n",
"| explained_variance | 0.984 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 29399 |\n",
"| policy_loss | 0.00104 |\n",
"| std | 0.256 |\n",
"| value_loss | 0.000154 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.71 |\n",
"| ep_rew_mean | -0.216 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 29500 |\n",
"| time_elapsed | 1929 |\n",
"| total_timesteps | 590000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.0789 |\n",
"| explained_variance | 0.976 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 29499 |\n",
"| policy_loss | -0.00463 |\n",
"| std | 0.256 |\n",
"| value_loss | 0.000125 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.68 |\n",
"| ep_rew_mean | -0.211 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 29600 |\n",
"| time_elapsed | 1936 |\n",
"| total_timesteps | 592000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.0721 |\n",
"| explained_variance | 0.957 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 29599 |\n",
"| policy_loss | 0.00372 |\n",
"| std | 0.256 |\n",
"| value_loss | 0.000154 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.73 |\n",
"| ep_rew_mean | -0.214 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 29700 |\n",
"| time_elapsed | 1942 |\n",
"| total_timesteps | 594000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.0523 |\n",
"| explained_variance | 0.944 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 29699 |\n",
"| policy_loss | -0.0172 |\n",
"| std | 0.254 |\n",
"| value_loss | 0.000583 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.73 |\n",
"| ep_rew_mean | -0.208 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 29800 |\n",
"| time_elapsed | 1949 |\n",
"| total_timesteps | 596000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.0378 |\n",
"| explained_variance | 0.978 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 29799 |\n",
"| policy_loss | -0.00199 |\n",
"| std | 0.253 |\n",
"| value_loss | 0.000118 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.81 |\n",
"| ep_rew_mean | -0.222 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 29900 |\n",
"| time_elapsed | 1955 |\n",
"| total_timesteps | 598000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.0337 |\n",
"| explained_variance | 0.941 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 29899 |\n",
"| policy_loss | -0.00225 |\n",
"| std | 0.253 |\n",
"| value_loss | 0.000302 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.7 |\n",
"| ep_rew_mean | -0.202 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 30000 |\n",
"| time_elapsed | 1962 |\n",
"| total_timesteps | 600000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.0211 |\n",
"| explained_variance | 0.957 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 29999 |\n",
"| policy_loss | 0.00179 |\n",
"| std | 0.252 |\n",
"| value_loss | 0.000195 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.68 |\n",
"| ep_rew_mean | -0.207 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 30100 |\n",
"| time_elapsed | 1968 |\n",
"| total_timesteps | 602000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.0145 |\n",
"| explained_variance | 0.967 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 30099 |\n",
"| policy_loss | 0.00233 |\n",
"| std | 0.251 |\n",
"| value_loss | 0.000175 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.68 |\n",
"| ep_rew_mean | -0.221 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 30200 |\n",
"| time_elapsed | 1975 |\n",
"| total_timesteps | 604000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.00944 |\n",
"| explained_variance | 0.977 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 30199 |\n",
"| policy_loss | 0.00867 |\n",
"| std | 0.251 |\n",
"| value_loss | 0.000269 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.76 |\n",
"| ep_rew_mean | -0.204 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 30300 |\n",
"| time_elapsed | 1981 |\n",
"| total_timesteps | 606000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.0259 |\n",
"| explained_variance | 0.896 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 30299 |\n",
"| policy_loss | 0.00392 |\n",
"| std | 0.253 |\n",
"| value_loss | 0.000621 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.53 |\n",
"| ep_rew_mean | -0.184 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 30400 |\n",
"| time_elapsed | 1987 |\n",
"| total_timesteps | 608000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.0218 |\n",
"| explained_variance | 0.954 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 30399 |\n",
"| policy_loss | 0.00193 |\n",
"| std | 0.252 |\n",
"| value_loss | 0.000178 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.71 |\n",
"| ep_rew_mean | -0.221 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 30500 |\n",
"| time_elapsed | 1994 |\n",
"| total_timesteps | 610000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.0179 |\n",
"| explained_variance | 0.97 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 30499 |\n",
"| policy_loss | -0.00915 |\n",
"| std | 0.252 |\n",
"| value_loss | 0.000349 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.68 |\n",
"| ep_rew_mean | -0.214 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 30600 |\n",
"| time_elapsed | 2000 |\n",
"| total_timesteps | 612000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.00891 |\n",
"| explained_variance | 0.985 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 30599 |\n",
"| policy_loss | 0.00139 |\n",
"| std | 0.251 |\n",
"| value_loss | 0.000114 |\n",
"------------------------------------\n",
"-------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.76 |\n",
"| ep_rew_mean | -0.211 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 30700 |\n",
"| time_elapsed | 2007 |\n",
"| total_timesteps | 614000 |\n",
"| train/ | |\n",
"| entropy_loss | -0.000173 |\n",
"| explained_variance | 0.957 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 30699 |\n",
"| policy_loss | -0.00162 |\n",
"| std | 0.25 |\n",
"| value_loss | 0.00027 |\n",
"-------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.69 |\n",
"| ep_rew_mean | -0.203 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 30800 |\n",
"| time_elapsed | 2013 |\n",
"| total_timesteps | 616000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.0335 |\n",
"| explained_variance | 0.991 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 30799 |\n",
"| policy_loss | 0.000278 |\n",
"| std | 0.248 |\n",
"| value_loss | 7.28e-05 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 3.6 |\n",
"| ep_rew_mean | -0.282 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 30900 |\n",
"| time_elapsed | 2020 |\n",
"| total_timesteps | 618000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.0436 |\n",
"| explained_variance | -0.101 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 30899 |\n",
"| policy_loss | 0.0141 |\n",
"| std | 0.247 |\n",
"| value_loss | 0.372 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.74 |\n",
"| ep_rew_mean | -0.197 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 31000 |\n",
"| time_elapsed | 2026 |\n",
"| total_timesteps | 620000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.0668 |\n",
"| explained_variance | 0.864 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 30999 |\n",
"| policy_loss | -0.0156 |\n",
"| std | 0.245 |\n",
"| value_loss | 0.000871 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 4.53 |\n",
"| ep_rew_mean | -0.351 |\n",
"| success_rate | 0.97 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 31100 |\n",
"| time_elapsed | 2033 |\n",
"| total_timesteps | 622000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.0879 |\n",
"| explained_variance | 0.968 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 31099 |\n",
"| policy_loss | -0.00268 |\n",
"| std | 0.243 |\n",
"| value_loss | 0.0172 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 9.92 |\n",
"| ep_rew_mean | -1.14 |\n",
"| success_rate | 0.86 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 31200 |\n",
"| time_elapsed | 2039 |\n",
"| total_timesteps | 624000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.0789 |\n",
"| explained_variance | 0.977 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 31199 |\n",
"| policy_loss | -0.111 |\n",
"| std | 0.243 |\n",
"| value_loss | 0.218 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 7.09 |\n",
"| ep_rew_mean | -0.661 |\n",
"| success_rate | 0.92 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 31300 |\n",
"| time_elapsed | 2047 |\n",
"| total_timesteps | 626000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.0698 |\n",
"| explained_variance | 0.932 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 31299 |\n",
"| policy_loss | 0.013 |\n",
"| std | 0.244 |\n",
"| value_loss | 0.495 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 4.32 |\n",
"| ep_rew_mean | -0.383 |\n",
"| success_rate | 0.97 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 31400 |\n",
"| time_elapsed | 2052 |\n",
"| total_timesteps | 628000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.0893 |\n",
"| explained_variance | 0.0255 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 31399 |\n",
"| policy_loss | -0.0874 |\n",
"| std | 0.243 |\n",
"| value_loss | 0.0304 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 3.23 |\n",
"| ep_rew_mean | -0.253 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 31500 |\n",
"| time_elapsed | 2059 |\n",
"| total_timesteps | 630000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.103 |\n",
"| explained_variance | 0.258 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 31499 |\n",
"| policy_loss | -0.00242 |\n",
"| std | 0.242 |\n",
"| value_loss | 0.0139 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 4.29 |\n",
"| ep_rew_mean | -0.335 |\n",
"| success_rate | 0.99 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 31600 |\n",
"| time_elapsed | 2065 |\n",
"| total_timesteps | 632000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.0958 |\n",
"| explained_variance | -2.39 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 31599 |\n",
"| policy_loss | -0.0277 |\n",
"| std | 0.243 |\n",
"| value_loss | 0.272 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.95 |\n",
"| ep_rew_mean | -0.234 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 31700 |\n",
"| time_elapsed | 2072 |\n",
"| total_timesteps | 634000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.108 |\n",
"| explained_variance | 0.322 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 31699 |\n",
"| policy_loss | -0.0126 |\n",
"| std | 0.242 |\n",
"| value_loss | 0.0109 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.78 |\n",
"| ep_rew_mean | -0.213 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 31800 |\n",
"| time_elapsed | 2078 |\n",
"| total_timesteps | 636000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.103 |\n",
"| explained_variance | 0.673 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 31799 |\n",
"| policy_loss | -0.0158 |\n",
"| std | 0.242 |\n",
"| value_loss | 0.00189 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.95 |\n",
"| ep_rew_mean | -0.235 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 31900 |\n",
"| time_elapsed | 2085 |\n",
"| total_timesteps | 638000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.118 |\n",
"| explained_variance | 0.889 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 31899 |\n",
"| policy_loss | 0.0057 |\n",
"| std | 0.241 |\n",
"| value_loss | 0.000871 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.81 |\n",
"| ep_rew_mean | -0.22 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 32000 |\n",
"| time_elapsed | 2091 |\n",
"| total_timesteps | 640000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.112 |\n",
"| explained_variance | 0.898 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 31999 |\n",
"| policy_loss | -0.0053 |\n",
"| std | 0.242 |\n",
"| value_loss | 0.000577 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.67 |\n",
"| ep_rew_mean | -0.204 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 32100 |\n",
"| time_elapsed | 2097 |\n",
"| total_timesteps | 642000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.138 |\n",
"| explained_variance | 0.905 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 32099 |\n",
"| policy_loss | -0.00074 |\n",
"| std | 0.24 |\n",
"| value_loss | 0.000423 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.78 |\n",
"| ep_rew_mean | -0.214 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 32200 |\n",
"| time_elapsed | 2104 |\n",
"| total_timesteps | 644000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.144 |\n",
"| explained_variance | 0.952 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 32199 |\n",
"| policy_loss | -0.00775 |\n",
"| std | 0.24 |\n",
"| value_loss | 0.000341 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.79 |\n",
"| ep_rew_mean | -0.222 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 32300 |\n",
"| time_elapsed | 2110 |\n",
"| total_timesteps | 646000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.143 |\n",
"| explained_variance | 0.826 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 32299 |\n",
"| policy_loss | -0.0022 |\n",
"| std | 0.239 |\n",
"| value_loss | 0.000872 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.81 |\n",
"| ep_rew_mean | -0.225 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 32400 |\n",
"| time_elapsed | 2117 |\n",
"| total_timesteps | 648000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.139 |\n",
"| explained_variance | 0.948 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 32399 |\n",
"| policy_loss | 0.00661 |\n",
"| std | 0.24 |\n",
"| value_loss | 0.00045 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 3.04 |\n",
"| ep_rew_mean | -0.24 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 32500 |\n",
"| time_elapsed | 2123 |\n",
"| total_timesteps | 650000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.143 |\n",
"| explained_variance | 0.535 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 32499 |\n",
"| policy_loss | 0.00974 |\n",
"| std | 0.239 |\n",
"| value_loss | 0.00648 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.9 |\n",
"| ep_rew_mean | -0.228 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 32600 |\n",
"| time_elapsed | 2130 |\n",
"| total_timesteps | 652000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.162 |\n",
"| explained_variance | 0.892 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 32599 |\n",
"| policy_loss | -0.035 |\n",
"| std | 0.238 |\n",
"| value_loss | 0.00291 |\n",
"------------------------------------\n",
"-------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.7 |\n",
"| ep_rew_mean | -0.21 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 32700 |\n",
"| time_elapsed | 2136 |\n",
"| total_timesteps | 654000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.163 |\n",
"| explained_variance | 0.894 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 32699 |\n",
"| policy_loss | -0.000635 |\n",
"| std | 0.238 |\n",
"| value_loss | 0.000914 |\n",
"-------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.74 |\n",
"| ep_rew_mean | -0.216 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 32800 |\n",
"| time_elapsed | 2143 |\n",
"| total_timesteps | 656000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.173 |\n",
"| explained_variance | 0.882 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 32799 |\n",
"| policy_loss | 0.00325 |\n",
"| std | 0.237 |\n",
"| value_loss | 0.00111 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.68 |\n",
"| ep_rew_mean | -0.204 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 32900 |\n",
"| time_elapsed | 2149 |\n",
"| total_timesteps | 658000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.177 |\n",
"| explained_variance | 0.948 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 32899 |\n",
"| policy_loss | 0.00785 |\n",
"| std | 0.237 |\n",
"| value_loss | 0.000491 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.75 |\n",
"| ep_rew_mean | -0.221 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 33000 |\n",
"| time_elapsed | 2156 |\n",
"| total_timesteps | 660000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.186 |\n",
"| explained_variance | 0.81 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 32999 |\n",
"| policy_loss | 0.00784 |\n",
"| std | 0.236 |\n",
"| value_loss | 0.00147 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.9 |\n",
"| ep_rew_mean | -0.231 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 33100 |\n",
"| time_elapsed | 2163 |\n",
"| total_timesteps | 662000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.202 |\n",
"| explained_variance | 0.924 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 33099 |\n",
"| policy_loss | 0.00504 |\n",
"| std | 0.235 |\n",
"| value_loss | 0.000827 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.83 |\n",
"| ep_rew_mean | -0.223 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 33200 |\n",
"| time_elapsed | 2170 |\n",
"| total_timesteps | 664000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.203 |\n",
"| explained_variance | 0.938 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 33199 |\n",
"| policy_loss | 0.000531 |\n",
"| std | 0.235 |\n",
"| value_loss | 0.000419 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 3.2 |\n",
"| ep_rew_mean | -0.255 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 33300 |\n",
"| time_elapsed | 2176 |\n",
"| total_timesteps | 666000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.218 |\n",
"| explained_variance | 0.651 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 33299 |\n",
"| policy_loss | 0.0165 |\n",
"| std | 0.234 |\n",
"| value_loss | 0.00543 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 3.02 |\n",
"| ep_rew_mean | -0.241 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 33400 |\n",
"| time_elapsed | 2183 |\n",
"| total_timesteps | 668000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.205 |\n",
"| explained_variance | 0.905 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 33399 |\n",
"| policy_loss | 0.0066 |\n",
"| std | 0.235 |\n",
"| value_loss | 0.000605 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.73 |\n",
"| ep_rew_mean | -0.215 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 33500 |\n",
"| time_elapsed | 2189 |\n",
"| total_timesteps | 670000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.202 |\n",
"| explained_variance | 0.933 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 33499 |\n",
"| policy_loss | 0.0121 |\n",
"| std | 0.235 |\n",
"| value_loss | 0.000487 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.63 |\n",
"| ep_rew_mean | -0.199 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 33600 |\n",
"| time_elapsed | 2196 |\n",
"| total_timesteps | 672000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.219 |\n",
"| explained_variance | 0.837 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 33599 |\n",
"| policy_loss | 0.00742 |\n",
"| std | 0.234 |\n",
"| value_loss | 0.000533 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.83 |\n",
"| ep_rew_mean | -0.223 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 33700 |\n",
"| time_elapsed | 2202 |\n",
"| total_timesteps | 674000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.224 |\n",
"| explained_variance | 0.936 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 33699 |\n",
"| policy_loss | -0.0106 |\n",
"| std | 0.234 |\n",
"| value_loss | 0.000459 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.66 |\n",
"| ep_rew_mean | -0.199 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 33800 |\n",
"| time_elapsed | 2209 |\n",
"| total_timesteps | 676000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.244 |\n",
"| explained_variance | 0.95 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 33799 |\n",
"| policy_loss | -0.0018 |\n",
"| std | 0.233 |\n",
"| value_loss | 0.000868 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.84 |\n",
"| ep_rew_mean | -0.218 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 33900 |\n",
"| time_elapsed | 2215 |\n",
"| total_timesteps | 678000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.262 |\n",
"| explained_variance | 0.955 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 33899 |\n",
"| policy_loss | 0.00138 |\n",
"| std | 0.231 |\n",
"| value_loss | 0.000271 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.76 |\n",
"| ep_rew_mean | -0.218 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 34000 |\n",
"| time_elapsed | 2222 |\n",
"| total_timesteps | 680000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.25 |\n",
"| explained_variance | 0.985 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 33999 |\n",
"| policy_loss | 0.00578 |\n",
"| std | 0.232 |\n",
"| value_loss | 0.000545 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.81 |\n",
"| ep_rew_mean | -0.226 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 34100 |\n",
"| time_elapsed | 2228 |\n",
"| total_timesteps | 682000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.244 |\n",
"| explained_variance | 0.988 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 34099 |\n",
"| policy_loss | -0.00433 |\n",
"| std | 0.232 |\n",
"| value_loss | 0.00021 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.8 |\n",
"| ep_rew_mean | -0.223 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 34200 |\n",
"| time_elapsed | 2235 |\n",
"| total_timesteps | 684000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.26 |\n",
"| explained_variance | 0.912 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 34199 |\n",
"| policy_loss | 0.00953 |\n",
"| std | 0.231 |\n",
"| value_loss | 0.000719 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.95 |\n",
"| ep_rew_mean | -0.23 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 34300 |\n",
"| time_elapsed | 2241 |\n",
"| total_timesteps | 686000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.266 |\n",
"| explained_variance | 0.972 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 34299 |\n",
"| policy_loss | -0.009 |\n",
"| std | 0.23 |\n",
"| value_loss | 0.000286 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.82 |\n",
"| ep_rew_mean | -0.22 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 34400 |\n",
"| time_elapsed | 2248 |\n",
"| total_timesteps | 688000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.254 |\n",
"| explained_variance | 0.963 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 34399 |\n",
"| policy_loss | 0.00874 |\n",
"| std | 0.231 |\n",
"| value_loss | 0.000306 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.75 |\n",
"| ep_rew_mean | -0.215 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 34500 |\n",
"| time_elapsed | 2254 |\n",
"| total_timesteps | 690000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.244 |\n",
"| explained_variance | 0.967 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 34499 |\n",
"| policy_loss | -0.00688 |\n",
"| std | 0.232 |\n",
"| value_loss | 0.000289 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.96 |\n",
"| ep_rew_mean | -0.243 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 34600 |\n",
"| time_elapsed | 2261 |\n",
"| total_timesteps | 692000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.264 |\n",
"| explained_variance | 0.942 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 34599 |\n",
"| policy_loss | -0.0204 |\n",
"| std | 0.23 |\n",
"| value_loss | 0.000579 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.61 |\n",
"| ep_rew_mean | -0.196 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 34700 |\n",
"| time_elapsed | 2268 |\n",
"| total_timesteps | 694000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.278 |\n",
"| explained_variance | 0.951 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 34699 |\n",
"| policy_loss | -0.00389 |\n",
"| std | 0.229 |\n",
"| value_loss | 0.000537 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.47 |\n",
"| ep_rew_mean | -0.191 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 34800 |\n",
"| time_elapsed | 2275 |\n",
"| total_timesteps | 696000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.263 |\n",
"| explained_variance | 0.97 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 34799 |\n",
"| policy_loss | 0.000191 |\n",
"| std | 0.23 |\n",
"| value_loss | 0.000338 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.76 |\n",
"| ep_rew_mean | -0.208 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 34900 |\n",
"| time_elapsed | 2281 |\n",
"| total_timesteps | 698000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.28 |\n",
"| explained_variance | 0.961 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 34899 |\n",
"| policy_loss | 0.00362 |\n",
"| std | 0.229 |\n",
"| value_loss | 0.000877 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.82 |\n",
"| ep_rew_mean | -0.218 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 35000 |\n",
"| time_elapsed | 2288 |\n",
"| total_timesteps | 700000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.289 |\n",
"| explained_variance | 0.942 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 34999 |\n",
"| policy_loss | 0.00205 |\n",
"| std | 0.228 |\n",
"| value_loss | 0.00034 |\n",
"------------------------------------\n",
"-------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.68 |\n",
"| ep_rew_mean | -0.197 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 35100 |\n",
"| time_elapsed | 2295 |\n",
"| total_timesteps | 702000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.296 |\n",
"| explained_variance | 0.987 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 35099 |\n",
"| policy_loss | -0.000645 |\n",
"| std | 0.227 |\n",
"| value_loss | 0.000152 |\n",
"-------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.8 |\n",
"| ep_rew_mean | -0.22 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 35200 |\n",
"| time_elapsed | 2303 |\n",
"| total_timesteps | 704000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.279 |\n",
"| explained_variance | 0.393 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 35199 |\n",
"| policy_loss | -0.0364 |\n",
"| std | 0.229 |\n",
"| value_loss | 0.00686 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.64 |\n",
"| ep_rew_mean | -0.21 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 35300 |\n",
"| time_elapsed | 2309 |\n",
"| total_timesteps | 706000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.287 |\n",
"| explained_variance | 0.976 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 35299 |\n",
"| policy_loss | -0.0075 |\n",
"| std | 0.228 |\n",
"| value_loss | 0.000388 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.56 |\n",
"| ep_rew_mean | -0.197 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 35400 |\n",
"| time_elapsed | 2317 |\n",
"| total_timesteps | 708000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.294 |\n",
"| explained_variance | 0.987 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 35399 |\n",
"| policy_loss | 0.00215 |\n",
"| std | 0.228 |\n",
"| value_loss | 0.000174 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.86 |\n",
"| ep_rew_mean | -0.23 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 35500 |\n",
"| time_elapsed | 2323 |\n",
"| total_timesteps | 710000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.308 |\n",
"| explained_variance | 0.988 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 35499 |\n",
"| policy_loss | -0.00456 |\n",
"| std | 0.227 |\n",
"| value_loss | 0.000256 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.97 |\n",
"| ep_rew_mean | -0.242 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 35600 |\n",
"| time_elapsed | 2329 |\n",
"| total_timesteps | 712000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.327 |\n",
"| explained_variance | 0.974 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 35599 |\n",
"| policy_loss | -0.00201 |\n",
"| std | 0.225 |\n",
"| value_loss | 0.000263 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.75 |\n",
"| ep_rew_mean | -0.213 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 35700 |\n",
"| time_elapsed | 2336 |\n",
"| total_timesteps | 714000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.334 |\n",
"| explained_variance | 0.832 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 35699 |\n",
"| policy_loss | -0.00775 |\n",
"| std | 0.224 |\n",
"| value_loss | 0.000996 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.86 |\n",
"| ep_rew_mean | -0.232 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 35800 |\n",
"| time_elapsed | 2342 |\n",
"| total_timesteps | 716000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.357 |\n",
"| explained_variance | 0.97 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 35799 |\n",
"| policy_loss | 0.00306 |\n",
"| std | 0.223 |\n",
"| value_loss | 0.000389 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.81 |\n",
"| ep_rew_mean | -0.234 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 35900 |\n",
"| time_elapsed | 2349 |\n",
"| total_timesteps | 718000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.368 |\n",
"| explained_variance | 0.98 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 35899 |\n",
"| policy_loss | -0.00652 |\n",
"| std | 0.223 |\n",
"| value_loss | 0.000801 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.81 |\n",
"| ep_rew_mean | -0.218 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 36000 |\n",
"| time_elapsed | 2354 |\n",
"| total_timesteps | 720000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.373 |\n",
"| explained_variance | 0.663 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 35999 |\n",
"| policy_loss | 0.000492 |\n",
"| std | 0.223 |\n",
"| value_loss | 0.00158 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.53 |\n",
"| ep_rew_mean | -0.185 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 36100 |\n",
"| time_elapsed | 2362 |\n",
"| total_timesteps | 722000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.384 |\n",
"| explained_variance | 0.974 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 36099 |\n",
"| policy_loss | -0.00366 |\n",
"| std | 0.222 |\n",
"| value_loss | 0.000187 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.64 |\n",
"| ep_rew_mean | -0.2 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 36200 |\n",
"| time_elapsed | 2367 |\n",
"| total_timesteps | 724000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.414 |\n",
"| explained_variance | 0.96 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 36199 |\n",
"| policy_loss | 0.000915 |\n",
"| std | 0.219 |\n",
"| value_loss | 0.000279 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.59 |\n",
"| ep_rew_mean | -0.188 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 36300 |\n",
"| time_elapsed | 2375 |\n",
"| total_timesteps | 726000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.428 |\n",
"| explained_variance | 0.97 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 36299 |\n",
"| policy_loss | -0.00048 |\n",
"| std | 0.218 |\n",
"| value_loss | 0.000291 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.7 |\n",
"| ep_rew_mean | -0.203 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 36400 |\n",
"| time_elapsed | 2380 |\n",
"| total_timesteps | 728000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.425 |\n",
"| explained_variance | 0.977 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 36399 |\n",
"| policy_loss | -0.00507 |\n",
"| std | 0.218 |\n",
"| value_loss | 0.000118 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.63 |\n",
"| ep_rew_mean | -0.204 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 36500 |\n",
"| time_elapsed | 2387 |\n",
"| total_timesteps | 730000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.437 |\n",
"| explained_variance | 0.988 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 36499 |\n",
"| policy_loss | -0.00125 |\n",
"| std | 0.218 |\n",
"| value_loss | 0.000147 |\n",
"------------------------------------\n",
"-------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.83 |\n",
"| ep_rew_mean | -0.231 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 36600 |\n",
"| time_elapsed | 2393 |\n",
"| total_timesteps | 732000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.452 |\n",
"| explained_variance | 0.97 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 36599 |\n",
"| policy_loss | -0.000152 |\n",
"| std | 0.216 |\n",
"| value_loss | 0.000198 |\n",
"-------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.81 |\n",
"| ep_rew_mean | -0.218 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 36700 |\n",
"| time_elapsed | 2400 |\n",
"| total_timesteps | 734000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.455 |\n",
"| explained_variance | 0.61 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 36699 |\n",
"| policy_loss | -0.0337 |\n",
"| std | 0.216 |\n",
"| value_loss | 0.00649 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.58 |\n",
"| ep_rew_mean | -0.192 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 36800 |\n",
"| time_elapsed | 2406 |\n",
"| total_timesteps | 736000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.484 |\n",
"| explained_variance | 0.996 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 36799 |\n",
"| policy_loss | 0.00167 |\n",
"| std | 0.214 |\n",
"| value_loss | 3.89e-05 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.72 |\n",
"| ep_rew_mean | -0.214 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 36900 |\n",
"| time_elapsed | 2413 |\n",
"| total_timesteps | 738000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.479 |\n",
"| explained_variance | 0.969 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 36899 |\n",
"| policy_loss | 0.00877 |\n",
"| std | 0.215 |\n",
"| value_loss | 0.0003 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.78 |\n",
"| ep_rew_mean | -0.223 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 37000 |\n",
"| time_elapsed | 2419 |\n",
"| total_timesteps | 740000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.476 |\n",
"| explained_variance | 0.981 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 36999 |\n",
"| policy_loss | 0.00234 |\n",
"| std | 0.215 |\n",
"| value_loss | 0.00018 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.81 |\n",
"| ep_rew_mean | -0.223 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 37100 |\n",
"| time_elapsed | 2426 |\n",
"| total_timesteps | 742000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.481 |\n",
"| explained_variance | 0.948 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 37099 |\n",
"| policy_loss | -0.0076 |\n",
"| std | 0.215 |\n",
"| value_loss | 0.00072 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.67 |\n",
"| ep_rew_mean | -0.195 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 37200 |\n",
"| time_elapsed | 2432 |\n",
"| total_timesteps | 744000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.501 |\n",
"| explained_variance | 0.976 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 37199 |\n",
"| policy_loss | -0.0106 |\n",
"| std | 0.214 |\n",
"| value_loss | 0.000162 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.83 |\n",
"| ep_rew_mean | -0.221 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 37300 |\n",
"| time_elapsed | 2439 |\n",
"| total_timesteps | 746000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.516 |\n",
"| explained_variance | 0.989 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 37299 |\n",
"| policy_loss | 0.00479 |\n",
"| std | 0.213 |\n",
"| value_loss | 0.000152 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.62 |\n",
"| ep_rew_mean | -0.198 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 37400 |\n",
"| time_elapsed | 2447 |\n",
"| total_timesteps | 748000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.521 |\n",
"| explained_variance | 0.957 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 37399 |\n",
"| policy_loss | 0.00017 |\n",
"| std | 0.213 |\n",
"| value_loss | 0.000284 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.73 |\n",
"| ep_rew_mean | -0.204 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 37500 |\n",
"| time_elapsed | 2453 |\n",
"| total_timesteps | 750000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.526 |\n",
"| explained_variance | 0.942 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 37499 |\n",
"| policy_loss | -0.012 |\n",
"| std | 0.213 |\n",
"| value_loss | 0.000577 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.81 |\n",
"| ep_rew_mean | -0.225 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 37600 |\n",
"| time_elapsed | 2459 |\n",
"| total_timesteps | 752000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.526 |\n",
"| explained_variance | 0.972 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 37599 |\n",
"| policy_loss | 0.00279 |\n",
"| std | 0.213 |\n",
"| value_loss | 0.000409 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.76 |\n",
"| ep_rew_mean | -0.214 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 37700 |\n",
"| time_elapsed | 2465 |\n",
"| total_timesteps | 754000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.522 |\n",
"| explained_variance | 0.917 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 37699 |\n",
"| policy_loss | 0.00561 |\n",
"| std | 0.213 |\n",
"| value_loss | 0.000557 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.77 |\n",
"| ep_rew_mean | -0.22 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 37800 |\n",
"| time_elapsed | 2472 |\n",
"| total_timesteps | 756000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.541 |\n",
"| explained_variance | 0.992 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 37799 |\n",
"| policy_loss | 0.00705 |\n",
"| std | 0.211 |\n",
"| value_loss | 0.000112 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.77 |\n",
"| ep_rew_mean | -0.21 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 37900 |\n",
"| time_elapsed | 2478 |\n",
"| total_timesteps | 758000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.566 |\n",
"| explained_variance | 0.961 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 37899 |\n",
"| policy_loss | -0.00871 |\n",
"| std | 0.209 |\n",
"| value_loss | 0.000288 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.71 |\n",
"| ep_rew_mean | -0.207 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 38000 |\n",
"| time_elapsed | 2485 |\n",
"| total_timesteps | 760000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.556 |\n",
"| explained_variance | 0.967 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 37999 |\n",
"| policy_loss | -0.0127 |\n",
"| std | 0.21 |\n",
"| value_loss | 0.000409 |\n",
"------------------------------------\n",
"-------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.86 |\n",
"| ep_rew_mean | -0.224 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 38100 |\n",
"| time_elapsed | 2491 |\n",
"| total_timesteps | 762000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.562 |\n",
"| explained_variance | 0.964 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 38099 |\n",
"| policy_loss | -0.000174 |\n",
"| std | 0.21 |\n",
"| value_loss | 0.000168 |\n",
"-------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.88 |\n",
"| ep_rew_mean | -0.228 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 38200 |\n",
"| time_elapsed | 2498 |\n",
"| total_timesteps | 764000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.579 |\n",
"| explained_variance | 0.979 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 38199 |\n",
"| policy_loss | -0.00283 |\n",
"| std | 0.208 |\n",
"| value_loss | 0.000179 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.85 |\n",
"| ep_rew_mean | -0.228 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 38300 |\n",
"| time_elapsed | 2503 |\n",
"| total_timesteps | 766000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.588 |\n",
"| explained_variance | 0.904 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 38299 |\n",
"| policy_loss | 0.00759 |\n",
"| std | 0.208 |\n",
"| value_loss | 0.000826 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.68 |\n",
"| ep_rew_mean | -0.209 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 38400 |\n",
"| time_elapsed | 2510 |\n",
"| total_timesteps | 768000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.6 |\n",
"| explained_variance | 0.975 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 38399 |\n",
"| policy_loss | 0.00472 |\n",
"| std | 0.207 |\n",
"| value_loss | 0.000252 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.93 |\n",
"| ep_rew_mean | -0.231 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 38500 |\n",
"| time_elapsed | 2516 |\n",
"| total_timesteps | 770000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.606 |\n",
"| explained_variance | 0.964 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 38499 |\n",
"| policy_loss | 0.00314 |\n",
"| std | 0.206 |\n",
"| value_loss | 0.000791 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.48 |\n",
"| ep_rew_mean | -0.179 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 38600 |\n",
"| time_elapsed | 2523 |\n",
"| total_timesteps | 772000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.618 |\n",
"| explained_variance | 0.951 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 38599 |\n",
"| policy_loss | 0.00734 |\n",
"| std | 0.206 |\n",
"| value_loss | 0.000312 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.83 |\n",
"| ep_rew_mean | -0.225 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 38700 |\n",
"| time_elapsed | 2529 |\n",
"| total_timesteps | 774000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.601 |\n",
"| explained_variance | 0.787 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 38699 |\n",
"| policy_loss | -0.0119 |\n",
"| std | 0.207 |\n",
"| value_loss | 0.000923 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.82 |\n",
"| ep_rew_mean | -0.22 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 38800 |\n",
"| time_elapsed | 2535 |\n",
"| total_timesteps | 776000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.601 |\n",
"| explained_variance | 0.975 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 38799 |\n",
"| policy_loss | 0.00146 |\n",
"| std | 0.207 |\n",
"| value_loss | 0.000233 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.68 |\n",
"| ep_rew_mean | -0.201 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 38900 |\n",
"| time_elapsed | 2541 |\n",
"| total_timesteps | 778000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.582 |\n",
"| explained_variance | 0.987 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 38899 |\n",
"| policy_loss | 0.00165 |\n",
"| std | 0.209 |\n",
"| value_loss | 6.08e-05 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.68 |\n",
"| ep_rew_mean | -0.215 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 39000 |\n",
"| time_elapsed | 2548 |\n",
"| total_timesteps | 780000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.585 |\n",
"| explained_variance | 0.991 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 38999 |\n",
"| policy_loss | 0.00448 |\n",
"| std | 0.209 |\n",
"| value_loss | 0.000115 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.68 |\n",
"| ep_rew_mean | -0.207 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 39100 |\n",
"| time_elapsed | 2554 |\n",
"| total_timesteps | 782000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.589 |\n",
"| explained_variance | 0.969 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 39099 |\n",
"| policy_loss | 0.00197 |\n",
"| std | 0.208 |\n",
"| value_loss | 0.00021 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.75 |\n",
"| ep_rew_mean | -0.214 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 39200 |\n",
"| time_elapsed | 2560 |\n",
"| total_timesteps | 784000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.597 |\n",
"| explained_variance | 0.922 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 39199 |\n",
"| policy_loss | 0.0108 |\n",
"| std | 0.208 |\n",
"| value_loss | 0.000328 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.59 |\n",
"| ep_rew_mean | -0.193 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 39300 |\n",
"| time_elapsed | 2567 |\n",
"| total_timesteps | 786000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.601 |\n",
"| explained_variance | 0.887 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 39299 |\n",
"| policy_loss | -0.00694 |\n",
"| std | 0.208 |\n",
"| value_loss | 0.000471 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.9 |\n",
"| ep_rew_mean | -0.228 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 39400 |\n",
"| time_elapsed | 2573 |\n",
"| total_timesteps | 788000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.601 |\n",
"| explained_variance | 0.98 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 39399 |\n",
"| policy_loss | 0.00564 |\n",
"| std | 0.208 |\n",
"| value_loss | 0.000154 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.73 |\n",
"| ep_rew_mean | -0.218 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 39500 |\n",
"| time_elapsed | 2580 |\n",
"| total_timesteps | 790000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.603 |\n",
"| explained_variance | 0.988 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 39499 |\n",
"| policy_loss | 0.00431 |\n",
"| std | 0.208 |\n",
"| value_loss | 0.000161 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.63 |\n",
"| ep_rew_mean | -0.2 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 39600 |\n",
"| time_elapsed | 2586 |\n",
"| total_timesteps | 792000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.615 |\n",
"| explained_variance | 0.981 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 39599 |\n",
"| policy_loss | -0.00309 |\n",
"| std | 0.207 |\n",
"| value_loss | 0.000374 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.65 |\n",
"| ep_rew_mean | -0.202 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 39700 |\n",
"| time_elapsed | 2593 |\n",
"| total_timesteps | 794000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.627 |\n",
"| explained_variance | 0.983 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 39699 |\n",
"| policy_loss | 0.00263 |\n",
"| std | 0.206 |\n",
"| value_loss | 0.000176 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.75 |\n",
"| ep_rew_mean | -0.214 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 39800 |\n",
"| time_elapsed | 2599 |\n",
"| total_timesteps | 796000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.649 |\n",
"| explained_variance | 0.959 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 39799 |\n",
"| policy_loss | -0.00185 |\n",
"| std | 0.204 |\n",
"| value_loss | 0.000135 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.78 |\n",
"| ep_rew_mean | -0.207 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 39900 |\n",
"| time_elapsed | 2606 |\n",
"| total_timesteps | 798000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.659 |\n",
"| explained_variance | 0.99 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 39899 |\n",
"| policy_loss | 0.00274 |\n",
"| std | 0.204 |\n",
"| value_loss | 6.57e-05 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.65 |\n",
"| ep_rew_mean | -0.202 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 40000 |\n",
"| time_elapsed | 2612 |\n",
"| total_timesteps | 800000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.66 |\n",
"| explained_variance | 0.96 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 39999 |\n",
"| policy_loss | 0.00813 |\n",
"| std | 0.204 |\n",
"| value_loss | 0.000281 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.69 |\n",
"| ep_rew_mean | -0.212 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 40100 |\n",
"| time_elapsed | 2619 |\n",
"| total_timesteps | 802000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.67 |\n",
"| explained_variance | 0.976 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 40099 |\n",
"| policy_loss | -0.00202 |\n",
"| std | 0.203 |\n",
"| value_loss | 0.000195 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.82 |\n",
"| ep_rew_mean | -0.219 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 40200 |\n",
"| time_elapsed | 2626 |\n",
"| total_timesteps | 804000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.691 |\n",
"| explained_variance | 0.902 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 40199 |\n",
"| policy_loss | -0.00684 |\n",
"| std | 0.201 |\n",
"| value_loss | 0.000408 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.54 |\n",
"| ep_rew_mean | -0.194 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 40300 |\n",
"| time_elapsed | 2633 |\n",
"| total_timesteps | 806000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.687 |\n",
"| explained_variance | 0.982 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 40299 |\n",
"| policy_loss | -0.00118 |\n",
"| std | 0.202 |\n",
"| value_loss | 0.000348 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.7 |\n",
"| ep_rew_mean | -0.205 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 40400 |\n",
"| time_elapsed | 2639 |\n",
"| total_timesteps | 808000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.696 |\n",
"| explained_variance | 0.913 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 40399 |\n",
"| policy_loss | 0.0108 |\n",
"| std | 0.202 |\n",
"| value_loss | 0.000923 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.73 |\n",
"| ep_rew_mean | -0.217 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 40500 |\n",
"| time_elapsed | 2646 |\n",
"| total_timesteps | 810000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.717 |\n",
"| explained_variance | 0.963 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 40499 |\n",
"| policy_loss | -0.0158 |\n",
"| std | 0.2 |\n",
"| value_loss | 0.000384 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.75 |\n",
"| ep_rew_mean | -0.214 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 40600 |\n",
"| time_elapsed | 2652 |\n",
"| total_timesteps | 812000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.708 |\n",
"| explained_variance | 0.976 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 40599 |\n",
"| policy_loss | 0.00278 |\n",
"| std | 0.201 |\n",
"| value_loss | 0.00015 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.81 |\n",
"| ep_rew_mean | -0.219 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 40700 |\n",
"| time_elapsed | 2659 |\n",
"| total_timesteps | 814000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.737 |\n",
"| explained_variance | 0.733 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 40699 |\n",
"| policy_loss | 0.0375 |\n",
"| std | 0.199 |\n",
"| value_loss | 0.0027 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.56 |\n",
"| ep_rew_mean | -0.197 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 40800 |\n",
"| time_elapsed | 2665 |\n",
"| total_timesteps | 816000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.746 |\n",
"| explained_variance | 0.973 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 40799 |\n",
"| policy_loss | -0.00953 |\n",
"| std | 0.198 |\n",
"| value_loss | 0.000261 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.62 |\n",
"| ep_rew_mean | -0.201 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 40900 |\n",
"| time_elapsed | 2672 |\n",
"| total_timesteps | 818000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.743 |\n",
"| explained_variance | 0.979 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 40899 |\n",
"| policy_loss | 0.00243 |\n",
"| std | 0.199 |\n",
"| value_loss | 0.000338 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.57 |\n",
"| ep_rew_mean | -0.198 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 41000 |\n",
"| time_elapsed | 2677 |\n",
"| total_timesteps | 820000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.744 |\n",
"| explained_variance | 0.976 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 40999 |\n",
"| policy_loss | -0.00429 |\n",
"| std | 0.198 |\n",
"| value_loss | 0.000165 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.79 |\n",
"| ep_rew_mean | -0.225 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 41100 |\n",
"| time_elapsed | 2684 |\n",
"| total_timesteps | 822000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.754 |\n",
"| explained_variance | 0.979 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 41099 |\n",
"| policy_loss | -0.00115 |\n",
"| std | 0.197 |\n",
"| value_loss | 0.000161 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.67 |\n",
"| ep_rew_mean | -0.207 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 41200 |\n",
"| time_elapsed | 2690 |\n",
"| total_timesteps | 824000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.762 |\n",
"| explained_variance | 0.974 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 41199 |\n",
"| policy_loss | 0.00196 |\n",
"| std | 0.197 |\n",
"| value_loss | 0.000124 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.62 |\n",
"| ep_rew_mean | -0.205 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 41300 |\n",
"| time_elapsed | 2697 |\n",
"| total_timesteps | 826000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.781 |\n",
"| explained_variance | 0.983 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 41299 |\n",
"| policy_loss | -0.00223 |\n",
"| std | 0.196 |\n",
"| value_loss | 0.00014 |\n",
"------------------------------------\n",
"-------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.83 |\n",
"| ep_rew_mean | -0.216 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 41400 |\n",
"| time_elapsed | 2703 |\n",
"| total_timesteps | 828000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.792 |\n",
"| explained_variance | 0.989 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 41399 |\n",
"| policy_loss | -2.58e-05 |\n",
"| std | 0.195 |\n",
"| value_loss | 9.67e-05 |\n",
"-------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.67 |\n",
"| ep_rew_mean | -0.2 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 41500 |\n",
"| time_elapsed | 2709 |\n",
"| total_timesteps | 830000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.778 |\n",
"| explained_variance | 0.959 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 41499 |\n",
"| policy_loss | -0.00308 |\n",
"| std | 0.196 |\n",
"| value_loss | 0.00018 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.84 |\n",
"| ep_rew_mean | -0.225 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 41600 |\n",
"| time_elapsed | 2717 |\n",
"| total_timesteps | 832000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.783 |\n",
"| explained_variance | 0.969 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 41599 |\n",
"| policy_loss | -0.00925 |\n",
"| std | 0.195 |\n",
"| value_loss | 0.00023 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.83 |\n",
"| ep_rew_mean | -0.221 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 41700 |\n",
"| time_elapsed | 2724 |\n",
"| total_timesteps | 834000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.79 |\n",
"| explained_variance | 0.87 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 41699 |\n",
"| policy_loss | -0.00221 |\n",
"| std | 0.195 |\n",
"| value_loss | 0.000564 |\n",
"------------------------------------\n",
"-------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.65 |\n",
"| ep_rew_mean | -0.204 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 41800 |\n",
"| time_elapsed | 2731 |\n",
"| total_timesteps | 836000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.804 |\n",
"| explained_variance | 0.969 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 41799 |\n",
"| policy_loss | -0.000451 |\n",
"| std | 0.194 |\n",
"| value_loss | 0.000328 |\n",
"-------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.81 |\n",
"| ep_rew_mean | -0.222 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 41900 |\n",
"| time_elapsed | 2737 |\n",
"| total_timesteps | 838000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.813 |\n",
"| explained_variance | 0.885 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 41899 |\n",
"| policy_loss | -0.00446 |\n",
"| std | 0.194 |\n",
"| value_loss | 0.00103 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.76 |\n",
"| ep_rew_mean | -0.222 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 42000 |\n",
"| time_elapsed | 2744 |\n",
"| total_timesteps | 840000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.817 |\n",
"| explained_variance | 0.986 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 41999 |\n",
"| policy_loss | 0.000841 |\n",
"| std | 0.193 |\n",
"| value_loss | 0.000105 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.93 |\n",
"| ep_rew_mean | -0.223 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 42100 |\n",
"| time_elapsed | 2750 |\n",
"| total_timesteps | 842000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.826 |\n",
"| explained_variance | 0.974 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 42099 |\n",
"| policy_loss | -0.00738 |\n",
"| std | 0.193 |\n",
"| value_loss | 0.000207 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.62 |\n",
"| ep_rew_mean | -0.2 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 42200 |\n",
"| time_elapsed | 2757 |\n",
"| total_timesteps | 844000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.829 |\n",
"| explained_variance | 0.608 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 42199 |\n",
"| policy_loss | 0.0719 |\n",
"| std | 0.193 |\n",
"| value_loss | 0.0107 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.61 |\n",
"| ep_rew_mean | -0.199 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 42300 |\n",
"| time_elapsed | 2763 |\n",
"| total_timesteps | 846000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.829 |\n",
"| explained_variance | 0.979 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 42299 |\n",
"| policy_loss | 0.00642 |\n",
"| std | 0.192 |\n",
"| value_loss | 0.000259 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.71 |\n",
"| ep_rew_mean | -0.205 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 42400 |\n",
"| time_elapsed | 2770 |\n",
"| total_timesteps | 848000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.834 |\n",
"| explained_variance | 0.969 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 42399 |\n",
"| policy_loss | -0.00928 |\n",
"| std | 0.192 |\n",
"| value_loss | 0.000162 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.73 |\n",
"| ep_rew_mean | -0.213 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 42500 |\n",
"| time_elapsed | 2776 |\n",
"| total_timesteps | 850000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.837 |\n",
"| explained_variance | 0.975 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 42499 |\n",
"| policy_loss | 0.00355 |\n",
"| std | 0.191 |\n",
"| value_loss | 0.000133 |\n",
"------------------------------------\n",
"-------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.55 |\n",
"| ep_rew_mean | -0.191 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 42600 |\n",
"| time_elapsed | 2783 |\n",
"| total_timesteps | 852000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.853 |\n",
"| explained_variance | 0.982 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 42599 |\n",
"| policy_loss | -0.000159 |\n",
"| std | 0.19 |\n",
"| value_loss | 0.000101 |\n",
"-------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.59 |\n",
"| ep_rew_mean | -0.198 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 42700 |\n",
"| time_elapsed | 2789 |\n",
"| total_timesteps | 854000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.871 |\n",
"| explained_variance | 0.974 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 42699 |\n",
"| policy_loss | 0.00216 |\n",
"| std | 0.19 |\n",
"| value_loss | 0.000125 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.69 |\n",
"| ep_rew_mean | -0.21 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 42800 |\n",
"| time_elapsed | 2795 |\n",
"| total_timesteps | 856000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.864 |\n",
"| explained_variance | 0.975 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 42799 |\n",
"| policy_loss | 0.0115 |\n",
"| std | 0.19 |\n",
"| value_loss | 0.000346 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.74 |\n",
"| ep_rew_mean | -0.212 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 42900 |\n",
"| time_elapsed | 2801 |\n",
"| total_timesteps | 858000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.869 |\n",
"| explained_variance | 0.988 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 42899 |\n",
"| policy_loss | -0.00131 |\n",
"| std | 0.19 |\n",
"| value_loss | 0.000107 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.7 |\n",
"| ep_rew_mean | -0.206 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 43000 |\n",
"| time_elapsed | 2808 |\n",
"| total_timesteps | 860000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.865 |\n",
"| explained_variance | 0.986 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 42999 |\n",
"| policy_loss | 0.00381 |\n",
"| std | 0.19 |\n",
"| value_loss | 0.000171 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.81 |\n",
"| ep_rew_mean | -0.224 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 43100 |\n",
"| time_elapsed | 2814 |\n",
"| total_timesteps | 862000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.881 |\n",
"| explained_variance | 0.989 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 43099 |\n",
"| policy_loss | -0.002 |\n",
"| std | 0.189 |\n",
"| value_loss | 0.000104 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.77 |\n",
"| ep_rew_mean | -0.218 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 43200 |\n",
"| time_elapsed | 2821 |\n",
"| total_timesteps | 864000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.881 |\n",
"| explained_variance | 0.993 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 43199 |\n",
"| policy_loss | -0.00621 |\n",
"| std | 0.189 |\n",
"| value_loss | 7.77e-05 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.69 |\n",
"| ep_rew_mean | -0.208 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 43300 |\n",
"| time_elapsed | 2827 |\n",
"| total_timesteps | 866000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.867 |\n",
"| explained_variance | 0.988 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 43299 |\n",
"| policy_loss | 0.00199 |\n",
"| std | 0.19 |\n",
"| value_loss | 0.000125 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.64 |\n",
"| ep_rew_mean | -0.203 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 43400 |\n",
"| time_elapsed | 2834 |\n",
"| total_timesteps | 868000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.868 |\n",
"| explained_variance | 0.984 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 43399 |\n",
"| policy_loss | -0.00647 |\n",
"| std | 0.19 |\n",
"| value_loss | 0.000139 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.67 |\n",
"| ep_rew_mean | -0.21 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 43500 |\n",
"| time_elapsed | 2840 |\n",
"| total_timesteps | 870000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.856 |\n",
"| explained_variance | 0.943 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 43499 |\n",
"| policy_loss | -0.004 |\n",
"| std | 0.191 |\n",
"| value_loss | 0.000446 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.64 |\n",
"| ep_rew_mean | -0.203 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 43600 |\n",
"| time_elapsed | 2846 |\n",
"| total_timesteps | 872000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.85 |\n",
"| explained_variance | 0.911 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 43599 |\n",
"| policy_loss | 0.00677 |\n",
"| std | 0.191 |\n",
"| value_loss | 0.000232 |\n",
"------------------------------------\n",
"-------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.7 |\n",
"| ep_rew_mean | -0.212 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 43700 |\n",
"| time_elapsed | 2853 |\n",
"| total_timesteps | 874000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.855 |\n",
"| explained_variance | 0.984 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 43699 |\n",
"| policy_loss | -0.000607 |\n",
"| std | 0.191 |\n",
"| value_loss | 0.000181 |\n",
"-------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.68 |\n",
"| ep_rew_mean | -0.204 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 43800 |\n",
"| time_elapsed | 2859 |\n",
"| total_timesteps | 876000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.852 |\n",
"| explained_variance | 0.933 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 43799 |\n",
"| policy_loss | 0.00514 |\n",
"| std | 0.191 |\n",
"| value_loss | 0.000506 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.58 |\n",
"| ep_rew_mean | -0.192 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 43900 |\n",
"| time_elapsed | 2866 |\n",
"| total_timesteps | 878000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.838 |\n",
"| explained_variance | 0.954 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 43899 |\n",
"| policy_loss | -0.00875 |\n",
"| std | 0.192 |\n",
"| value_loss | 0.000284 |\n",
"------------------------------------\n",
"-------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.71 |\n",
"| ep_rew_mean | -0.21 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 44000 |\n",
"| time_elapsed | 2871 |\n",
"| total_timesteps | 880000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.841 |\n",
"| explained_variance | 0.987 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 43999 |\n",
"| policy_loss | -0.000598 |\n",
"| std | 0.192 |\n",
"| value_loss | 0.000108 |\n",
"-------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.75 |\n",
"| ep_rew_mean | -0.215 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 44100 |\n",
"| time_elapsed | 2879 |\n",
"| total_timesteps | 882000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.829 |\n",
"| explained_variance | 0.975 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 44099 |\n",
"| policy_loss | 0.00538 |\n",
"| std | 0.193 |\n",
"| value_loss | 0.00022 |\n",
"------------------------------------\n",
"-------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.64 |\n",
"| ep_rew_mean | -0.205 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 44200 |\n",
"| time_elapsed | 2884 |\n",
"| total_timesteps | 884000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.848 |\n",
"| explained_variance | 0.983 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 44199 |\n",
"| policy_loss | -0.000168 |\n",
"| std | 0.191 |\n",
"| value_loss | 0.000104 |\n",
"-------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.72 |\n",
"| ep_rew_mean | -0.21 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 44300 |\n",
"| time_elapsed | 2892 |\n",
"| total_timesteps | 886000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.853 |\n",
"| explained_variance | 0.994 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 44299 |\n",
"| policy_loss | 0.000868 |\n",
"| std | 0.191 |\n",
"| value_loss | 7.55e-05 |\n",
"------------------------------------\n",
"-------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.63 |\n",
"| ep_rew_mean | -0.199 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 44400 |\n",
"| time_elapsed | 2898 |\n",
"| total_timesteps | 888000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.857 |\n",
"| explained_variance | 0.995 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 44399 |\n",
"| policy_loss | -0.000826 |\n",
"| std | 0.191 |\n",
"| value_loss | 8.98e-05 |\n",
"-------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.62 |\n",
"| ep_rew_mean | -0.198 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 44500 |\n",
"| time_elapsed | 2905 |\n",
"| total_timesteps | 890000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.872 |\n",
"| explained_variance | 0.994 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 44499 |\n",
"| policy_loss | 0.00331 |\n",
"| std | 0.19 |\n",
"| value_loss | 5.43e-05 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.63 |\n",
"| ep_rew_mean | -0.204 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 44600 |\n",
"| time_elapsed | 2911 |\n",
"| total_timesteps | 892000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.885 |\n",
"| explained_variance | 0.971 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 44599 |\n",
"| policy_loss | 0.00155 |\n",
"| std | 0.19 |\n",
"| value_loss | 0.000174 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.7 |\n",
"| ep_rew_mean | -0.204 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 44700 |\n",
"| time_elapsed | 2918 |\n",
"| total_timesteps | 894000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.888 |\n",
"| explained_variance | 0.979 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 44699 |\n",
"| policy_loss | 0.00673 |\n",
"| std | 0.189 |\n",
"| value_loss | 0.000173 |\n",
"------------------------------------\n",
"-------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.79 |\n",
"| ep_rew_mean | -0.213 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 44800 |\n",
"| time_elapsed | 2924 |\n",
"| total_timesteps | 896000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.891 |\n",
"| explained_variance | 0.989 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 44799 |\n",
"| policy_loss | -8.09e-05 |\n",
"| std | 0.189 |\n",
"| value_loss | 0.000114 |\n",
"-------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.88 |\n",
"| ep_rew_mean | -0.234 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 44900 |\n",
"| time_elapsed | 2931 |\n",
"| total_timesteps | 898000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.872 |\n",
"| explained_variance | 0.987 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 44899 |\n",
"| policy_loss | -0.00133 |\n",
"| std | 0.191 |\n",
"| value_loss | 0.000126 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.73 |\n",
"| ep_rew_mean | -0.207 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 45000 |\n",
"| time_elapsed | 2937 |\n",
"| total_timesteps | 900000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.881 |\n",
"| explained_variance | 0.992 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 44999 |\n",
"| policy_loss | 0.0064 |\n",
"| std | 0.19 |\n",
"| value_loss | 0.000112 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.73 |\n",
"| ep_rew_mean | -0.212 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 45100 |\n",
"| time_elapsed | 2944 |\n",
"| total_timesteps | 902000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.865 |\n",
"| explained_variance | 0.985 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 45099 |\n",
"| policy_loss | -0.00394 |\n",
"| std | 0.191 |\n",
"| value_loss | 0.000103 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.8 |\n",
"| ep_rew_mean | -0.223 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 45200 |\n",
"| time_elapsed | 2950 |\n",
"| total_timesteps | 904000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.914 |\n",
"| explained_variance | 0.975 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 45199 |\n",
"| policy_loss | -0.00122 |\n",
"| std | 0.188 |\n",
"| value_loss | 0.000302 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.7 |\n",
"| ep_rew_mean | -0.205 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 45300 |\n",
"| time_elapsed | 2957 |\n",
"| total_timesteps | 906000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.908 |\n",
"| explained_variance | 0.995 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 45299 |\n",
"| policy_loss | 0.00591 |\n",
"| std | 0.188 |\n",
"| value_loss | 0.000113 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.6 |\n",
"| ep_rew_mean | -0.199 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 45400 |\n",
"| time_elapsed | 2964 |\n",
"| total_timesteps | 908000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.905 |\n",
"| explained_variance | 0.977 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 45399 |\n",
"| policy_loss | -0.00185 |\n",
"| std | 0.189 |\n",
"| value_loss | 0.000156 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.63 |\n",
"| ep_rew_mean | -0.195 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 45500 |\n",
"| time_elapsed | 2970 |\n",
"| total_timesteps | 910000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.893 |\n",
"| explained_variance | 0.951 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 45499 |\n",
"| policy_loss | 0.0124 |\n",
"| std | 0.19 |\n",
"| value_loss | 0.000479 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.67 |\n",
"| ep_rew_mean | -0.2 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 45600 |\n",
"| time_elapsed | 2977 |\n",
"| total_timesteps | 912000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.911 |\n",
"| explained_variance | 0.991 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 45599 |\n",
"| policy_loss | -0.00692 |\n",
"| std | 0.188 |\n",
"| value_loss | 0.000114 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.62 |\n",
"| ep_rew_mean | -0.196 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 45700 |\n",
"| time_elapsed | 2983 |\n",
"| total_timesteps | 914000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.944 |\n",
"| explained_variance | 0.981 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 45699 |\n",
"| policy_loss | 0.00311 |\n",
"| std | 0.186 |\n",
"| value_loss | 9.87e-05 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.87 |\n",
"| ep_rew_mean | -0.232 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 45800 |\n",
"| time_elapsed | 2990 |\n",
"| total_timesteps | 916000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.962 |\n",
"| explained_variance | 0.985 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 45799 |\n",
"| policy_loss | -0.00825 |\n",
"| std | 0.185 |\n",
"| value_loss | 0.000116 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.74 |\n",
"| ep_rew_mean | -0.21 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 45900 |\n",
"| time_elapsed | 2996 |\n",
"| total_timesteps | 918000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.971 |\n",
"| explained_variance | 0.837 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 45899 |\n",
"| policy_loss | -0.00379 |\n",
"| std | 0.184 |\n",
"| value_loss | 0.000819 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.7 |\n",
"| ep_rew_mean | -0.207 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 46000 |\n",
"| time_elapsed | 3005 |\n",
"| total_timesteps | 920000 |\n",
"| train/ | |\n",
"| entropy_loss | 1 |\n",
"| explained_variance | 0.983 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 45999 |\n",
"| policy_loss | -0.00814 |\n",
"| std | 0.183 |\n",
"| value_loss | 0.000103 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.78 |\n",
"| ep_rew_mean | -0.22 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 46100 |\n",
"| time_elapsed | 3011 |\n",
"| total_timesteps | 922000 |\n",
"| train/ | |\n",
"| entropy_loss | 1 |\n",
"| explained_variance | 0.938 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 46099 |\n",
"| policy_loss | 0.0151 |\n",
"| std | 0.183 |\n",
"| value_loss | 0.000621 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.81 |\n",
"| ep_rew_mean | -0.225 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 46200 |\n",
"| time_elapsed | 3019 |\n",
"| total_timesteps | 924000 |\n",
"| train/ | |\n",
"| entropy_loss | 0.999 |\n",
"| explained_variance | 0.979 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 46199 |\n",
"| policy_loss | -0.00565 |\n",
"| std | 0.183 |\n",
"| value_loss | 0.000319 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.69 |\n",
"| ep_rew_mean | -0.212 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 46300 |\n",
"| time_elapsed | 3025 |\n",
"| total_timesteps | 926000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.03 |\n",
"| explained_variance | 0.963 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 46299 |\n",
"| policy_loss | -0.015 |\n",
"| std | 0.181 |\n",
"| value_loss | 0.000426 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.67 |\n",
"| ep_rew_mean | -0.209 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 46400 |\n",
"| time_elapsed | 3032 |\n",
"| total_timesteps | 928000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.03 |\n",
"| explained_variance | 0.992 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 46399 |\n",
"| policy_loss | 0.00804 |\n",
"| std | 0.181 |\n",
"| value_loss | 0.000216 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.82 |\n",
"| ep_rew_mean | -0.224 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 46500 |\n",
"| time_elapsed | 3038 |\n",
"| total_timesteps | 930000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.04 |\n",
"| explained_variance | 0.973 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 46499 |\n",
"| policy_loss | 0.00782 |\n",
"| std | 0.18 |\n",
"| value_loss | 0.000223 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.67 |\n",
"| ep_rew_mean | -0.205 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 46600 |\n",
"| time_elapsed | 3046 |\n",
"| total_timesteps | 932000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.06 |\n",
"| explained_variance | 0.976 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 46599 |\n",
"| policy_loss | -0.0125 |\n",
"| std | 0.179 |\n",
"| value_loss | 0.000248 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.73 |\n",
"| ep_rew_mean | -0.213 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 46700 |\n",
"| time_elapsed | 3052 |\n",
"| total_timesteps | 934000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.06 |\n",
"| explained_variance | 0.976 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 46699 |\n",
"| policy_loss | 0.00171 |\n",
"| std | 0.179 |\n",
"| value_loss | 0.000139 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.54 |\n",
"| ep_rew_mean | -0.196 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 46800 |\n",
"| time_elapsed | 3059 |\n",
"| total_timesteps | 936000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.06 |\n",
"| explained_variance | 0.992 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 46799 |\n",
"| policy_loss | 0.00604 |\n",
"| std | 0.179 |\n",
"| value_loss | 0.000146 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.64 |\n",
"| ep_rew_mean | -0.205 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 306 |\n",
"| iterations | 46900 |\n",
"| time_elapsed | 3065 |\n",
"| total_timesteps | 938000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.07 |\n",
"| explained_variance | 0.497 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 46899 |\n",
"| policy_loss | -0.0571 |\n",
"| std | 0.179 |\n",
"| value_loss | 0.00679 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.6 |\n",
"| ep_rew_mean | -0.191 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 47000 |\n",
"| time_elapsed | 3072 |\n",
"| total_timesteps | 940000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.08 |\n",
"| explained_variance | 0.933 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 46999 |\n",
"| policy_loss | -0.0424 |\n",
"| std | 0.179 |\n",
"| value_loss | 0.00136 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.86 |\n",
"| ep_rew_mean | -0.225 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 47100 |\n",
"| time_elapsed | 3078 |\n",
"| total_timesteps | 942000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.1 |\n",
"| explained_variance | 0.969 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 47099 |\n",
"| policy_loss | -0.00619 |\n",
"| std | 0.178 |\n",
"| value_loss | 0.00103 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.81 |\n",
"| ep_rew_mean | -0.223 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 47200 |\n",
"| time_elapsed | 3085 |\n",
"| total_timesteps | 944000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.11 |\n",
"| explained_variance | 0.911 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 47199 |\n",
"| policy_loss | 0.0139 |\n",
"| std | 0.177 |\n",
"| value_loss | 0.0015 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 3.38 |\n",
"| ep_rew_mean | -0.267 |\n",
"| success_rate | 0.99 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 47300 |\n",
"| time_elapsed | 3092 |\n",
"| total_timesteps | 946000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.11 |\n",
"| explained_variance | 0.897 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 47299 |\n",
"| policy_loss | 0.135 |\n",
"| std | 0.177 |\n",
"| value_loss | 0.103 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.62 |\n",
"| ep_rew_mean | -0.2 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 47400 |\n",
"| time_elapsed | 3099 |\n",
"| total_timesteps | 948000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.12 |\n",
"| explained_variance | 0.408 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 47399 |\n",
"| policy_loss | 0.0339 |\n",
"| std | 0.177 |\n",
"| value_loss | 0.00642 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.63 |\n",
"| ep_rew_mean | -0.197 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 47500 |\n",
"| time_elapsed | 3105 |\n",
"| total_timesteps | 950000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.13 |\n",
"| explained_variance | 0.981 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 47499 |\n",
"| policy_loss | 0.00971 |\n",
"| std | 0.176 |\n",
"| value_loss | 0.000172 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.77 |\n",
"| ep_rew_mean | -0.219 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 47600 |\n",
"| time_elapsed | 3112 |\n",
"| total_timesteps | 952000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.12 |\n",
"| explained_variance | 0.981 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 47599 |\n",
"| policy_loss | 0.00133 |\n",
"| std | 0.176 |\n",
"| value_loss | 0.000231 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.62 |\n",
"| ep_rew_mean | -0.2 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 47700 |\n",
"| time_elapsed | 3118 |\n",
"| total_timesteps | 954000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.11 |\n",
"| explained_variance | 0.938 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 47699 |\n",
"| policy_loss | -0.0245 |\n",
"| std | 0.177 |\n",
"| value_loss | 0.000652 |\n",
"------------------------------------\n",
"-------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.64 |\n",
"| ep_rew_mean | -0.199 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 47800 |\n",
"| time_elapsed | 3125 |\n",
"| total_timesteps | 956000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.12 |\n",
"| explained_variance | 0.97 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 47799 |\n",
"| policy_loss | -0.000551 |\n",
"| std | 0.177 |\n",
"| value_loss | 0.000333 |\n",
"-------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.72 |\n",
"| ep_rew_mean | -0.214 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 47900 |\n",
"| time_elapsed | 3132 |\n",
"| total_timesteps | 958000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.12 |\n",
"| explained_variance | 0.989 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 47899 |\n",
"| policy_loss | -0.00506 |\n",
"| std | 0.177 |\n",
"| value_loss | 8.59e-05 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.65 |\n",
"| ep_rew_mean | -0.211 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 48000 |\n",
"| time_elapsed | 3138 |\n",
"| total_timesteps | 960000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.14 |\n",
"| explained_variance | 0.974 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 47999 |\n",
"| policy_loss | 0.00703 |\n",
"| std | 0.176 |\n",
"| value_loss | 0.000297 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.52 |\n",
"| ep_rew_mean | -0.178 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 48100 |\n",
"| time_elapsed | 3145 |\n",
"| total_timesteps | 962000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.13 |\n",
"| explained_variance | 0.908 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 48099 |\n",
"| policy_loss | -0.00607 |\n",
"| std | 0.176 |\n",
"| value_loss | 0.000338 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.64 |\n",
"| ep_rew_mean | -0.2 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 48200 |\n",
"| time_elapsed | 3152 |\n",
"| total_timesteps | 964000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.11 |\n",
"| explained_variance | 0.992 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 48199 |\n",
"| policy_loss | 0.000962 |\n",
"| std | 0.177 |\n",
"| value_loss | 5.99e-05 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.63 |\n",
"| ep_rew_mean | -0.197 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 48300 |\n",
"| time_elapsed | 3158 |\n",
"| total_timesteps | 966000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.12 |\n",
"| explained_variance | 0.974 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 48299 |\n",
"| policy_loss | -0.0179 |\n",
"| std | 0.176 |\n",
"| value_loss | 0.000265 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.69 |\n",
"| ep_rew_mean | -0.212 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 48400 |\n",
"| time_elapsed | 3165 |\n",
"| total_timesteps | 968000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.15 |\n",
"| explained_variance | 0.975 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 48399 |\n",
"| policy_loss | -0.00674 |\n",
"| std | 0.175 |\n",
"| value_loss | 0.00025 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.88 |\n",
"| ep_rew_mean | -0.244 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 48500 |\n",
"| time_elapsed | 3172 |\n",
"| total_timesteps | 970000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.16 |\n",
"| explained_variance | 0.992 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 48499 |\n",
"| policy_loss | 0.00239 |\n",
"| std | 0.175 |\n",
"| value_loss | 0.000114 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.84 |\n",
"| ep_rew_mean | -0.227 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 48600 |\n",
"| time_elapsed | 3178 |\n",
"| total_timesteps | 972000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.18 |\n",
"| explained_variance | 0.953 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 48599 |\n",
"| policy_loss | 0.0156 |\n",
"| std | 0.174 |\n",
"| value_loss | 0.000273 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.6 |\n",
"| ep_rew_mean | -0.193 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 48700 |\n",
"| time_elapsed | 3185 |\n",
"| total_timesteps | 974000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.18 |\n",
"| explained_variance | 0.969 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 48699 |\n",
"| policy_loss | -0.00403 |\n",
"| std | 0.174 |\n",
"| value_loss | 0.000116 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.7 |\n",
"| ep_rew_mean | -0.208 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 48800 |\n",
"| time_elapsed | 3191 |\n",
"| total_timesteps | 976000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.19 |\n",
"| explained_variance | 0.97 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 48799 |\n",
"| policy_loss | 0.0127 |\n",
"| std | 0.173 |\n",
"| value_loss | 0.000284 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.6 |\n",
"| ep_rew_mean | -0.194 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 48900 |\n",
"| time_elapsed | 3199 |\n",
"| total_timesteps | 978000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.19 |\n",
"| explained_variance | 0.951 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 48899 |\n",
"| policy_loss | 0.00498 |\n",
"| std | 0.173 |\n",
"| value_loss | 0.000417 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.73 |\n",
"| ep_rew_mean | -0.204 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 49000 |\n",
"| time_elapsed | 3205 |\n",
"| total_timesteps | 980000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.2 |\n",
"| explained_variance | 0.96 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 48999 |\n",
"| policy_loss | 0.00689 |\n",
"| std | 0.172 |\n",
"| value_loss | 0.000513 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.65 |\n",
"| ep_rew_mean | -0.207 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 49100 |\n",
"| time_elapsed | 3212 |\n",
"| total_timesteps | 982000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.19 |\n",
"| explained_variance | 0.95 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 49099 |\n",
"| policy_loss | 0.0108 |\n",
"| std | 0.173 |\n",
"| value_loss | 0.000502 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.72 |\n",
"| ep_rew_mean | -0.219 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 49200 |\n",
"| time_elapsed | 3217 |\n",
"| total_timesteps | 984000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.21 |\n",
"| explained_variance | 0.974 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 49199 |\n",
"| policy_loss | -0.00175 |\n",
"| std | 0.171 |\n",
"| value_loss | 0.000104 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.8 |\n",
"| ep_rew_mean | -0.217 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 49300 |\n",
"| time_elapsed | 3225 |\n",
"| total_timesteps | 986000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.23 |\n",
"| explained_variance | 0.977 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 49299 |\n",
"| policy_loss | -0.0018 |\n",
"| std | 0.17 |\n",
"| value_loss | 0.000198 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.68 |\n",
"| ep_rew_mean | -0.203 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 49400 |\n",
"| time_elapsed | 3230 |\n",
"| total_timesteps | 988000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.21 |\n",
"| explained_variance | 0.942 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 49399 |\n",
"| policy_loss | 0.00639 |\n",
"| std | 0.172 |\n",
"| value_loss | 0.000212 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.77 |\n",
"| ep_rew_mean | -0.209 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 49500 |\n",
"| time_elapsed | 3238 |\n",
"| total_timesteps | 990000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.21 |\n",
"| explained_variance | 0.981 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 49499 |\n",
"| policy_loss | 0.00873 |\n",
"| std | 0.172 |\n",
"| value_loss | 0.000195 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.7 |\n",
"| ep_rew_mean | -0.207 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 49600 |\n",
"| time_elapsed | 3244 |\n",
"| total_timesteps | 992000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.22 |\n",
"| explained_variance | 0.884 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 49599 |\n",
"| policy_loss | 0.0116 |\n",
"| std | 0.171 |\n",
"| value_loss | 0.000657 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.64 |\n",
"| ep_rew_mean | -0.204 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 49700 |\n",
"| time_elapsed | 3251 |\n",
"| total_timesteps | 994000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.21 |\n",
"| explained_variance | 0.959 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 49699 |\n",
"| policy_loss | -0.00236 |\n",
"| std | 0.171 |\n",
"| value_loss | 0.00025 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.71 |\n",
"| ep_rew_mean | -0.203 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 49800 |\n",
"| time_elapsed | 3257 |\n",
"| total_timesteps | 996000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.22 |\n",
"| explained_variance | 0.973 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 49799 |\n",
"| policy_loss | 0.000928 |\n",
"| std | 0.171 |\n",
"| value_loss | 0.000305 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.81 |\n",
"| ep_rew_mean | -0.218 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 49900 |\n",
"| time_elapsed | 3264 |\n",
"| total_timesteps | 998000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.22 |\n",
"| explained_variance | 0.982 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 49899 |\n",
"| policy_loss | 0.0187 |\n",
"| std | 0.171 |\n",
"| value_loss | 0.000211 |\n",
"------------------------------------\n",
"------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 2.52 |\n",
"| ep_rew_mean | -0.186 |\n",
"| success_rate | 1 |\n",
"| time/ | |\n",
"| fps | 305 |\n",
"| iterations | 50000 |\n",
"| time_elapsed | 3270 |\n",
"| total_timesteps | 1000000 |\n",
"| train/ | |\n",
"| entropy_loss | 1.24 |\n",
"| explained_variance | 0.987 |\n",
"| learning_rate | 0.0007 |\n",
"| n_updates | 49999 |\n",
"| policy_loss | 0.00764 |\n",
"| std | 0.169 |\n",
"| value_loss | 0.000173 |\n",
"------------------------------------\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
""
]
},
"metadata": {},
"execution_count": 10
}
]
},
{
"cell_type": "markdown",
"source": [
"Saving the modela nd Vecnormalize the statistics when saving the agent"
],
"metadata": {
"id": "w3xmesRRA_dq"
}
},
{
"cell_type": "code",
"source": [
"# Save the model and VecNormalize statistics when saving the agent\n",
"model.save(\"a2c-PandaReachDense-v3\")\n",
"env.save(\"vec_normalize.pkl\")"
],
"metadata": {
"id": "zvUkwZ8GrcY7"
},
"execution_count": 11,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"Evaluating the Agent"
],
"metadata": {
"id": "6Q8RV6HBrk9k"
}
},
{
"cell_type": "code",
"source": [
"from stable_baselines3.common.vec_env import DummyVecEnv, VecNormalize\n",
"\n",
"# Load the saved statistics\n",
"eval_env = DummyVecEnv([lambda: gym.make(\"PandaReachDense-v3\")])\n",
"eval_env = VecNormalize.load(\"vec_normalize.pkl\", eval_env)\n",
"\n",
"# We need to override the render_mode\n",
"eval_env.render_mode = \"rgb_array\"\n",
"\n",
"# do not update them at test time\n",
"eval_env.training = False\n",
"# reward normalization is not needed at test time\n",
"eval_env.norm_reward = False\n",
"\n",
"# Load the agent\n",
"model = A2C.load(\"a2c-PandaReachDense-v3\")\n",
"\n",
"mean_reward, std_reward = evaluate_policy(model, eval_env)\n",
"\n",
"print(f\"Mean reward = {mean_reward:.2f} +/- {std_reward:.2f}\")"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
},
"id": "t7veIVTlrfT_",
"outputId": "3696d0c3-3f39-460f-fd89-2cfff688901a"
},
"execution_count": 12,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Mean reward = -0.16 +/- 0.08\n"
]
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"/usr/local/lib/python3.10/dist-packages/stable_baselines3/common/evaluation.py:67: UserWarning: Evaluation environment is not wrapped with a ``Monitor`` wrapper. This may result in reporting modified episode lengths and rewards, if other wrappers happen to modify these. Consider wrapping environment first with ``Monitor`` wrapper.\n",
" warnings.warn(\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"notebook_login()\n",
"!git config --global credential.helper store"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 145,
"referenced_widgets": [
"8ff8c13284c14676b06e4745721752ff",
"0f76ed54c37841919f69e3177fd6d7ec",
"e4cf51a9ec524655885fa9d07495fb38",
"767318ed9ad944be8f48ad555be1e1ff",
"bc645f00ff0f43cf859068ea57352721",
"3e660dd6ce074fd8bdf4a8244dd8b7a9",
"c0ae0beb39ca47d38ce6c970aaa1b61e",
"2bc31dd7c1de48d987ef760bf2d15147",
"12e0ce2415404baaaff00fea8d956d54",
"39949b8863224db28a986fe21017325c",
"aa046de0210e4c449ba575e1c36bacb1",
"9955e32bd5ae46268f8d9722622d174e",
"25b7d7c4c9e84d10b9965d53a63546c0",
"cff0d261124249a68f95b38739010ca5",
"1839eb1041f546ea8d52cb0d6f8c4c8a",
"b96787f8562c4dbc9d56ddcf52a32712",
"e1ba30e7cf0546329471a3f6f5e0b4bc",
"27216c11c3594a509ba423dd639459b5",
"a78a804660594c2abf59eca6eca50572",
"ef36b661ee3c4502a5cbe5f7766f154d",
"16c9ddf0f69f48a08f2ba7b0767c6e04",
"15902149c92341eb96bde04388332f92",
"ef37ebf8ddfa4a54aa6e6ff22a80e1ff",
"589a3dee05d14f978c816c5e160e3c6d",
"8097ed945e114ed5b87a4972d6f0d859",
"0f5dccb7a8b44ac79b70340cbc5db798",
"8cd6e4522ef44d69b8b723af315e7237",
"1cf3cc18ec1a4fb99655a5fc01bd1b22",
"86587e674adc46748f3246f6db7bd632",
"ba7dea34ec104c019006105901393e76",
"821d176ebe3a4bf5afcc2fe8a731a242",
"d0c0c8758616405786ab2144705b72c8"
]
},
"id": "k0zr35arCK1c",
"outputId": "d0ceda32-ecf7-4c47-fdd6-679b5b494247"
},
"execution_count": 21,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"VBox(children=(HTML(value='