{
"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": {
"96ab2b48ede34f369b6eae8d3473897f": {
"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_17fbbdd9e0444ef7b20842c3cc59b345",
"IPY_MODEL_864e1e7bcc4b430eba7ba686376c0e8a",
"IPY_MODEL_e8707d8c9ffd4a22a273a702b8e1e316",
"IPY_MODEL_ca7d6f64d2c545438d40731b9f955159"
],
"layout": "IPY_MODEL_8d86630525dc4b39aafb8074d2e262b0"
}
},
"e8d79186fcdc4ef0868c833180761f62": {
"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_a81c5bf9a5e344368cc1b942708bdb63",
"placeholder": "",
"style": "IPY_MODEL_37770393ceda4ec89408f749b4159606",
"value": " your Hugging Face\ntokens page and paste it below. "
}
},
"138e17534b7c4f6d84473fffd6f88bd7": {
"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_6e230407612c4722bf2df2f9a55d241d",
"placeholder": "",
"style": "IPY_MODEL_68d93ffd427d4b88b6200c3b2988f7f5",
"value": ""
}
},
"1a4e0cd0133548d992e6c5adebe90aa0": {
"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_78115d3432584e26a3b9732f23529d4c",
"style": "IPY_MODEL_66ff63784e49429098363abe06af82ab",
"value": true
}
},
"1e46fd051f2243fa839124f4ede1e9f3": {
"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_2c2fdc4bb2304afaa257093dfd5e9214",
"style": "IPY_MODEL_901b2ed4d68341acb17f85a38931f02e",
"tooltip": ""
}
},
"85b97b194f5746c5a2cfb85421bf7cfb": {
"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_a2262b9caf1041e6adf8121716d1b32b",
"placeholder": "",
"style": "IPY_MODEL_a551515ddf7c4c6fac9d7bc5737cc4bb",
"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. "
}
},
"8d86630525dc4b39aafb8074d2e262b0": {
"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%"
}
},
"a81c5bf9a5e344368cc1b942708bdb63": {
"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
}
},
"37770393ceda4ec89408f749b4159606": {
"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": ""
}
},
"6e230407612c4722bf2df2f9a55d241d": {
"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
}
},
"68d93ffd427d4b88b6200c3b2988f7f5": {
"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": ""
}
},
"78115d3432584e26a3b9732f23529d4c": {
"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
}
},
"66ff63784e49429098363abe06af82ab": {
"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": ""
}
},
"2c2fdc4bb2304afaa257093dfd5e9214": {
"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
}
},
"901b2ed4d68341acb17f85a38931f02e": {
"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": ""
}
},
"a2262b9caf1041e6adf8121716d1b32b": {
"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
}
},
"a551515ddf7c4c6fac9d7bc5737cc4bb": {
"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": ""
}
},
"550b83b4923d493d85733e903e7ffd01": {
"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_a64d097488804935a75f26a05b33c666",
"placeholder": "",
"style": "IPY_MODEL_4ad9891b73f74bedbcb59824f12bd7ee",
"value": "Connecting..."
}
},
"a64d097488804935a75f26a05b33c666": {
"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
}
},
"4ad9891b73f74bedbcb59824f12bd7ee": {
"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": ""
}
},
"17fbbdd9e0444ef7b20842c3cc59b345": {
"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_6df7400442be4771b3d84d9428a9b908",
"placeholder": "",
"style": "IPY_MODEL_5a604c84e40e4b8c94b113ec9261e327",
"value": "Token is valid (permission: write)."
}
},
"864e1e7bcc4b430eba7ba686376c0e8a": {
"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_ff5158df6e7348cdb3f240943502a03f",
"placeholder": "",
"style": "IPY_MODEL_87532f73bbc24354a95c28f1ba44f453",
"value": "Your token has been saved in your configured git credential helpers (store)."
}
},
"e8707d8c9ffd4a22a273a702b8e1e316": {
"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_ef04a55379e449ac97b916089e84b0da",
"placeholder": "",
"style": "IPY_MODEL_ad83925317804af3ba2f427c6ce33d66",
"value": "Your token has been saved to /root/.cache/huggingface/token"
}
},
"ca7d6f64d2c545438d40731b9f955159": {
"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_bb37f4b335f84236bf76040a99a3c66b",
"placeholder": "",
"style": "IPY_MODEL_8fb75f60269045929b86a00599724e94",
"value": "Login successful"
}
},
"6df7400442be4771b3d84d9428a9b908": {
"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
}
},
"5a604c84e40e4b8c94b113ec9261e327": {
"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": ""
}
},
"ff5158df6e7348cdb3f240943502a03f": {
"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
}
},
"87532f73bbc24354a95c28f1ba44f453": {
"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": ""
}
},
"ef04a55379e449ac97b916089e84b0da": {
"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
}
},
"ad83925317804af3ba2f427c6ce33d66": {
"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": ""
}
},
"bb37f4b335f84236bf76040a99a3c66b": {
"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
}
},
"8fb75f60269045929b86a00599724e94": {
"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": ""
}
},
"edfb62e479184b83b511a41219ce0669": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_13441d30aecc4f64ab9f3c0e41772436",
"IPY_MODEL_ce6704a2661043939195a0cddc117953",
"IPY_MODEL_2869a474bf414891a0897096ebb9f444"
],
"layout": "IPY_MODEL_b24aaa30a4804ca7a7ad3d86f184aa30"
}
},
"13441d30aecc4f64ab9f3c0e41772436": {
"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_c1a5f80239794291834f18a3f36a2a72",
"placeholder": "",
"style": "IPY_MODEL_8fffae92c9aa403880e35fcbe61cdb86",
"value": "Upload 4 LFS files: 100%"
}
},
"ce6704a2661043939195a0cddc117953": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_0fa2c171db4e458e8d62631ff898f09c",
"max": 4,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_1e811c1a5974409f8d2e4238b56dccaa",
"value": 4
}
},
"2869a474bf414891a0897096ebb9f444": {
"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_7125fe68a60a4538a7632cd463ccb05d",
"placeholder": "",
"style": "IPY_MODEL_07dacc45823f46928a4bcaa3a0dc5d51",
"value": " 4/4 [00:01<00:00, 1.72s/it]"
}
},
"b24aaa30a4804ca7a7ad3d86f184aa30": {
"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
}
},
"c1a5f80239794291834f18a3f36a2a72": {
"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
}
},
"8fffae92c9aa403880e35fcbe61cdb86": {
"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": ""
}
},
"0fa2c171db4e458e8d62631ff898f09c": {
"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
}
},
"1e811c1a5974409f8d2e4238b56dccaa": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"7125fe68a60a4538a7632cd463ccb05d": {
"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
}
},
"07dacc45823f46928a4bcaa3a0dc5d51": {
"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": ""
}
},
"da821995d6a342b1be7c2dbd1bec7f3a": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_8d1b259a9263495e93f86b9a1de204f1",
"IPY_MODEL_7b3ec54bc09b4699a08d0d74973365c3",
"IPY_MODEL_a55eeea40d0a4b2eb9f384e0c3e30437"
],
"layout": "IPY_MODEL_5736d5232c474f628af47dec086d8ec4"
}
},
"8d1b259a9263495e93f86b9a1de204f1": {
"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_5cd5025ed6df4da6941266efcbbc5ac7",
"placeholder": "",
"style": "IPY_MODEL_9f04db0080e4404c9e3349df72935c1b",
"value": "pytorch_variables.pth: 100%"
}
},
"7b3ec54bc09b4699a08d0d74973365c3": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_90fef320fc7e4961a42044d5fdcf0373",
"max": 431,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_86f485b29295443185709c8275eae644",
"value": 431
}
},
"a55eeea40d0a4b2eb9f384e0c3e30437": {
"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_a36b34351959495f8b48258b59747152",
"placeholder": "",
"style": "IPY_MODEL_a1c2c7a8a9ce476d89a4e3f9dd3ef743",
"value": " 431/431 [00:01<00:00, 466B/s]"
}
},
"5736d5232c474f628af47dec086d8ec4": {
"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
}
},
"5cd5025ed6df4da6941266efcbbc5ac7": {
"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
}
},
"9f04db0080e4404c9e3349df72935c1b": {
"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": ""
}
},
"90fef320fc7e4961a42044d5fdcf0373": {
"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
}
},
"86f485b29295443185709c8275eae644": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"a36b34351959495f8b48258b59747152": {
"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
}
},
"a1c2c7a8a9ce476d89a4e3f9dd3ef743": {
"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": ""
}
},
"56ce8d629b7a46729b19e8329ae09bb4": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_c8c6f75ac9844630bcaae0d026ba2542",
"IPY_MODEL_dd5d707431394713828bc09d6a00a8c2",
"IPY_MODEL_1b211f2a23c3462fa161a497e9e678c1"
],
"layout": "IPY_MODEL_370aee3cbcc84a94a9d29448c518c0e6"
}
},
"c8c6f75ac9844630bcaae0d026ba2542": {
"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_45fef11946b24d7d839ba77536459bce",
"placeholder": "",
"style": "IPY_MODEL_1bc7c17b8df4478a93320b57d6e5afe7",
"value": "policy.pth: 100%"
}
},
"dd5d707431394713828bc09d6a00a8c2": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_6f81f039df6f4a31a957cba9c31e26e0",
"max": 43329,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_7d82afef2d0a4b9592fcd21bcf606776",
"value": 43329
}
},
"1b211f2a23c3462fa161a497e9e678c1": {
"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_81ef6f5a734a43718160088983759725",
"placeholder": "",
"style": "IPY_MODEL_d5d21e52f0ea444f8a09370f8dfdc13f",
"value": " 43.3k/43.3k [00:01<00:00, 17.3kB/s]"
}
},
"370aee3cbcc84a94a9d29448c518c0e6": {
"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
}
},
"45fef11946b24d7d839ba77536459bce": {
"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
}
},
"1bc7c17b8df4478a93320b57d6e5afe7": {
"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": ""
}
},
"6f81f039df6f4a31a957cba9c31e26e0": {
"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
}
},
"7d82afef2d0a4b9592fcd21bcf606776": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"81ef6f5a734a43718160088983759725": {
"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
}
},
"d5d21e52f0ea444f8a09370f8dfdc13f": {
"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": ""
}
},
"467718e9125a4b06bbfbb9645c501b7f": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_a0776809249d450291cca98c76e75156",
"IPY_MODEL_4bf473386a774cd1a749bb9314bfa42f",
"IPY_MODEL_3517fdfdd1834e769246092c82ca7539"
],
"layout": "IPY_MODEL_34c45604e0cc4acdb69c52f328552e39"
}
},
"a0776809249d450291cca98c76e75156": {
"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_24cc1fddaf62432882c1b34cd513f6e8",
"placeholder": "",
"style": "IPY_MODEL_edbee8ab2c844c7faf3190b142e4577e",
"value": "policy.optimizer.pth: 100%"
}
},
"4bf473386a774cd1a749bb9314bfa42f": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_994fa44a8fbc4f17ab57841856c8dba4",
"max": 87929,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_d11e1d74baee43a5b109b399fdb89b8a",
"value": 87929
}
},
"3517fdfdd1834e769246092c82ca7539": {
"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_e0a7daff252942af8ba3751ade32528d",
"placeholder": "",
"style": "IPY_MODEL_452ec7ea9ce948e6b36f6907b676350a",
"value": " 87.9k/87.9k [00:01<00:00, 17.5kB/s]"
}
},
"34c45604e0cc4acdb69c52f328552e39": {
"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
}
},
"24cc1fddaf62432882c1b34cd513f6e8": {
"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
}
},
"edbee8ab2c844c7faf3190b142e4577e": {
"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": ""
}
},
"994fa44a8fbc4f17ab57841856c8dba4": {
"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
}
},
"d11e1d74baee43a5b109b399fdb89b8a": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"e0a7daff252942af8ba3751ade32528d": {
"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
}
},
"452ec7ea9ce948e6b36f6907b676350a": {
"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": ""
}
},
"28714c1d4cb442e99172a3ef96bec492": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_ecc96a6285e646f79ceef6a276d145a3",
"IPY_MODEL_e1b6f39001de4267927b2d3532061d80",
"IPY_MODEL_eb887492fa6342aa81a52e25519f6667"
],
"layout": "IPY_MODEL_f9368d5087914aeebb783eeb5f9c8871"
}
},
"ecc96a6285e646f79ceef6a276d145a3": {
"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_6704f68ac10043e0894afe37df3f2faf",
"placeholder": "",
"style": "IPY_MODEL_f616a5ede49f4b789ccbd986645ba11f",
"value": "ppo-LunarLander-v2.zip: 100%"
}
},
"e1b6f39001de4267927b2d3532061d80": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_63b30a2d1f794f808553613616801cb2",
"max": 146742,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_8ce50e4c8ff74953973f7d02e7345da7",
"value": 146742
}
},
"eb887492fa6342aa81a52e25519f6667": {
"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_b55111721bd34d5b9638729140357842",
"placeholder": "",
"style": "IPY_MODEL_b31d1a0c407e4ced96ff2dc9be56cc5a",
"value": " 147k/147k [00:01<00:00, 18.3kB/s]"
}
},
"f9368d5087914aeebb783eeb5f9c8871": {
"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
}
},
"6704f68ac10043e0894afe37df3f2faf": {
"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
}
},
"f616a5ede49f4b789ccbd986645ba11f": {
"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": ""
}
},
"63b30a2d1f794f808553613616801cb2": {
"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
}
},
"8ce50e4c8ff74953973f7d02e7345da7": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"b55111721bd34d5b9638729140357842": {
"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
}
},
"b31d1a0c407e4ced96ff2dc9be56cc5a": {
"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": ""
}
},
"40483e1b5a9e47928fa5787e7f52f486": {
"model_module": "@jupyter-widgets/controls",
"model_name": "HBoxModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_35baae5e2c7f49949ccb9b4298ddce39",
"IPY_MODEL_dc06c86c0acd41ca8616c76e55dfeb55",
"IPY_MODEL_c386ac68558c4598a32e01a7eec835b1"
],
"layout": "IPY_MODEL_c37d97a3fa9a465abfc13ca97bb01709"
}
},
"35baae5e2c7f49949ccb9b4298ddce39": {
"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_4e860d0d9c0e439b81373f8c70c45d4a",
"placeholder": "",
"style": "IPY_MODEL_1f70bb1afe25415f8c7bfd42222b579b",
"value": "Downloading ppo-LunarLander-v2.zip: 100%"
}
},
"dc06c86c0acd41ca8616c76e55dfeb55": {
"model_module": "@jupyter-widgets/controls",
"model_name": "FloatProgressModel",
"model_module_version": "1.5.0",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_98d25a66d61147db875af377a4fc2070",
"max": 145900,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_1ef8cea9ecb74bf38ea2763933d2a69d",
"value": 145900
}
},
"c386ac68558c4598a32e01a7eec835b1": {
"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_2e9cc7b9bd3a4e5f8e6b85ac2aa51f9e",
"placeholder": "",
"style": "IPY_MODEL_5e62fef035f34dfdb0a8865ba3ea85c7",
"value": " 146k/146k [00:00<00:00, 902kB/s]"
}
},
"c37d97a3fa9a465abfc13ca97bb01709": {
"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
}
},
"4e860d0d9c0e439b81373f8c70c45d4a": {
"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
}
},
"1f70bb1afe25415f8c7bfd42222b579b": {
"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": ""
}
},
"98d25a66d61147db875af377a4fc2070": {
"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
}
},
"1ef8cea9ecb74bf38ea2763933d2a69d": {
"model_module": "@jupyter-widgets/controls",
"model_name": "ProgressStyleModel",
"model_module_version": "1.5.0",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"2e9cc7b9bd3a4e5f8e6b85ac2aa51f9e": {
"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
}
},
"5e62fef035f34dfdb0a8865ba3ea85c7": {
"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": [
"#INTRODUCTION TO REINFORCEMENT LEARNING\n",
"\n",
"Deep RL is a type of Machine Learning where an agent learns how to behave in an environment by performing actions and seeing the results.\n",
"\n",
"In this first unit, you’ll learn the foundations of Deep Reinforcement Learning.\n",
"\n",
"Then, you’ll train your Deep Reinforcement Learning agent, a lunar lander to land correctly on the Moon using Stable-Baselines3 , a Deep Reinforcement Learning library.\n",
"\n",
"The big picture\n",
"The idea behind Reinforcement Learning is that an agent (an AI) will learn from the environment by interacting with it (through trial and error) and receiving rewards (negative or positive) as feedback for performing actions.\n",
"\n",
"Learning from interactions with the environment comes from our natural experiences.\n",
"\n",
"For instance, imagine putting your little brother in front of a video game he never played, giving him a controller, and leaving him alone.\n",
"\n",
"By interacting with his environment through trial and error, your little brother understands that he needs to get coins in this environment but avoid the enemies.\n",
"\n",
"Without any supervision, the child will get better and better at playing the game.\n",
"\n",
"That’s how humans and animals learn, through interaction. Reinforcement Learning is just a computational approach of learning from actions.\n"
],
"metadata": {
"id": "815EWzdb5qJZ"
}
},
{
"cell_type": "markdown",
"source": [
"Reinforcement learning is a framework for solving control tasks (also called decision problems) by building agents that learn from the environment by interacting with it through trial and error and receiving rewards (positive or negative) as unique feedback."
],
"metadata": {
"id": "c5BcKOa27-KK"
}
},
{
"cell_type": "markdown",
"source": [
"Markov Property\n",
"In papers, you’ll see that the RL process is called a Markov Decision Process (MDP).\n",
"\n",
"We’ll talk again about the Markov Property in the following units. But if you need to remember something today about it, it’s this: the Markov Property implies that our agent needs only the current state to decide what action to take and not the history of all the states and actions they took before.\n",
"\n",
"\n",
"1. Episodic task\n",
"In this case, we have a starting point and an ending point (a terminal state). This creates an episode: a list of States, Actions, Rewards, and new States.\n",
"\n",
"For instance, think about Super Mario Bros: an episode begin at the launch of a new Mario Level and ends when you’re killed or you reached the end of the level.\n",
"\n",
"2. Continuing tasks\n",
"These are tasks that continue forever (no terminal state). In this case, the agent must learn how to choose the best actions and simultaneously interact with the environment.\n",
"\n",
"For instance, an agent that does automated stock trading. For this task, there is no starting point and terminal state. The agent keeps running until we decide to stop it.\n",
"\n",
""
],
"metadata": {
"id": "0MIoKFvp8Zgw"
}
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 421
},
"id": "hCyBdADG4pAy",
"outputId": "6ab24363-3287-4ec2-9195-9d18448b65de"
},
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
""
],
"text/html": [
""
]
},
"metadata": {},
"execution_count": 1
}
]
},
{
"cell_type": "markdown",
"source": [
"# Import the packages"
],
"metadata": {
"id": "5FDc9-WtBYA7"
}
},
{
"cell_type": "code",
"source": [
"import gymnasium\n",
"\n",
"from huggingface_sb3 import load_from_hub, package_to_hub\n",
"from huggingface_hub import notebook_login # To log to our Hugging Face account to be able to upload models to the Hub.\n",
"\n",
"from stable_baselines3 import PPO\n",
"from stable_baselines3.common.env_util import make_vec_env\n",
"from stable_baselines3.common.evaluation import evaluate_policy\n",
"from stable_baselines3.common.monitor import Monitor"
],
"metadata": {
"id": "u4WJaMZnBZBD"
},
"execution_count": 2,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"Understand Gymnasium and how it works 🤖\n",
"🏋 The library containing our environment is called Gymnasium. You’ll use Gymnasium a lot in Deep Reinforcement Learning.\n",
"\n",
"Gymnasium is the new version of Gym library maintained by the Farama Foundation.\n",
"\n",
"The Gymnasium library provides two things:\n",
"\n",
"An interface that allows you to create RL environments.\n",
"A collection of environments (gym-control, atari, box2D…).\n",
"Let’s look at an example, but first let’s recall the RL loop.\n",
"\n",
""
],
"metadata": {
"id": "lcvb_yVhBwCE"
}
},
{
"cell_type": "markdown",
"source": [
"At each step:\n",
"- Our Agent receives a **state (S0)** from the **Environment** — we receive the first frame of our game (Environment).\n",
"- Based on that **state (S0),** the Agent takes an **action (A0)** — our Agent will move to the right.\n",
"- The environment transitions to a **new** **state (S1)** — new frame.\n",
"- The environment gives some **reward (R1)** to the Agent — we’re not dead *(Positive Reward +1)*.\n",
"\n",
"\n",
"With Gymnasium:\n",
"\n",
"1️⃣ We create our environment using `gymnasium.make()`\n",
"\n",
"2️⃣ We reset the environment to its initial state with `observation = env.reset()`\n",
"\n",
"At each step:\n",
"\n",
"3️⃣ Get an action using our model (in our example we take a random action)\n",
"\n",
"4️⃣ Using `env.step(action)`, we perform this action in the environment and get\n",
"- `observation`: The new state (st+1)\n",
"- `reward`: The reward we get after executing the action\n",
"- `terminated`: Indicates if the episode terminated (agent reach the terminal state)\n",
"- `truncated`: Introduced with this new version, it indicates a timelimit or if an agent go out of bounds of the environment for instance.\n",
"- `info`: A dictionary that provides additional information (depends on the environment).\n",
"\n",
"For more explanations check this 👉 https://gymnasium.farama.org/api/env/#gymnasium.Env.step\n",
"\n",
"If the episode is terminated:\n",
"- We reset the environment to its initial state with `observation = env.reset()`\n",
"\n",
"**Let's look at an example!** Make sure to read the code"
],
"metadata": {
"id": "BoS1LcIiCHVh"
}
},
{
"cell_type": "markdown",
"source": [
"LunarLander-v2 (Discrete)\n",
"\n",
"Landing pad is always at coordinates (0,0). Coordinates are the first two numbers in state vector. Reward for moving from the top of the screen to landing pad and zero speed is about 100..140 points. If lander moves away from landing pad it loses reward back. Episode finishes if the lander crashes or comes to rest, receiving additional -100 or +100 points. Each leg ground contact is +10. Firing main engine is -0.3 points each frame. Solved is 200 points. Landing outside landing pad is possible. Fuel is infinite, so an agent can learn to fly and then land on its first attempt. Four discrete actions available: do nothing, fire left orientation engine, fire main engine, fire right orientation engine.\n",
"\n",
"LunarLander-v2 is a scenario developed by Oleg Klimov, an engineer at OpenAI, inspired by the original Atari Lunar Lander (https://github.com/olegklimov). In the implementation, you have to take your landing pod to a lunar pad that is always located at coordinates x=0 and y=0. In addition, your actual x and y position is known since their values are stored in the first two elements of the state vector, the vector that contains all the information for the reinforcement learning algorithm to decide the best action to take at a certain moment.\n",
"Source: https://learning.oreilly.com/library/view/tensorflow-deep-learning/9781788398060/04be3bfb-74a9-44eb-8ecb-de954e7696fb.xhtml"
],
"metadata": {
"id": "UEBRk7fOC8en"
}
},
{
"cell_type": "code",
"source": [
"import gymnasium as gym\n",
"\n",
"# First, we create our environment called LunarLander-v2\n",
"env = gym.make(\"LunarLander-v2\")\n",
"\n",
"# Then we reset this environment\n",
"observation, info = env.reset()\n",
"\n",
"for _ in range(20):\n",
" # Take a random action\n",
" action = env.action_space.sample()\n",
" print(\"Action taken:\", action)\n",
"\n",
" # Do this action in the environment and get\n",
" # next_state, reward, terminated, truncated and info\n",
" observation, reward, terminated, truncated, info = env.step(action)\n",
"\n",
" # If the game is terminated (in our case we land, crashed) or truncated (timeout)\n",
" if terminated or truncated:\n",
" # Reset the environment\n",
" print(\"Environment is reset\")\n",
" observation, info = env.reset()\n",
"\n",
"env.close()"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "Y-qUEt8bBl7i",
"outputId": "e0dd08d7-6029-4c09-912f-7d984161ee3e"
},
"execution_count": 3,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Action taken: 0\n",
"Action taken: 2\n",
"Action taken: 3\n",
"Action taken: 1\n",
"Action taken: 3\n",
"Action taken: 1\n",
"Action taken: 3\n",
"Action taken: 3\n",
"Action taken: 0\n",
"Action taken: 3\n",
"Action taken: 1\n",
"Action taken: 0\n",
"Action taken: 2\n",
"Action taken: 1\n",
"Action taken: 1\n",
"Action taken: 2\n",
"Action taken: 0\n",
"Action taken: 1\n",
"Action taken: 2\n",
"Action taken: 2\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"## Create the LunarLander environment 🌛 and understand how it works\n",
"\n",
"### [The environment 🎮](https://gymnasium.farama.org/environments/box2d/lunar_lander/)\n",
"\n",
"In this first tutorial, we’re going to train our agent, a [Lunar Lander](https://gymnasium.farama.org/environments/box2d/lunar_lander/), **to land correctly on the moon**. To do that, the agent needs to learn **to adapt its speed and position (horizontal, vertical, and angular) to land correctly.**\n",
"\n",
"---\n",
"\n",
"\n",
"💡 A good habit when you start to use an environment is to check its documentation\n",
"\n",
"👉 https://gymnasium.farama.org/environments/box2d/lunar_lander/\n",
"\n",
"---\n"
],
"metadata": {
"id": "HK83xW2JFIGE"
}
},
{
"cell_type": "code",
"source": [
"# We create our environment with gym.make(\"\")\n",
"env = gym.make(\"LunarLander-v2\")\n",
"env.reset()\n",
"print(\"_____OBSERVATION SPACE_____ \\n\")\n",
"print(\"Observation Space Shape\", env.observation_space.shape)\n",
"print(\"Sample observation\", env.observation_space.sample()) # Get a random observation"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "UpiLc4-ADZTO",
"outputId": "2575af98-87b3-4deb-ac54-c2f46fd81b51"
},
"execution_count": 4,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"_____OBSERVATION SPACE_____ \n",
"\n",
"Observation Space Shape (8,)\n",
"Sample observation [-20.141338 -59.90314 4.230214 0.14666176 -1.7034489\n",
" -4.502537 0.61853015 0.20563099]\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"#### Vectorized Environment\n",
"\n",
"- We create a vectorized environment (a method for stacking multiple independent environments into a single environment) of 16 environments, this way, **we'll have more diverse experiences during the training.**"
],
"metadata": {
"id": "4vDMrd_ZHJPM"
}
},
{
"cell_type": "code",
"source": [
"# Create the environment\n",
"env = make_vec_env('LunarLander-v2', n_envs=16)"
],
"metadata": {
"id": "SsD7-kp-HD4X"
},
"execution_count": 5,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"## Create the Model 🤖\n",
"- We have studied our environment and we understood the problem: **being able to land the Lunar Lander to the Landing Pad correctly by controlling left, right and main orientation engine**. Now let's build the algorithm we're going to use to solve this Problem 🚀.\n",
"\n",
"- To do so, we're going to use our first Deep RL library, [Stable Baselines3 (SB3)](https://stable-baselines3.readthedocs.io/en/master/).\n",
"\n",
"- SB3 is a set of **reliable implementations of reinforcement learning algorithms in PyTorch**.\n",
"\n",
"---\n",
"\n",
"💡 A good habit when using a new library is to dive first on the documentation: https://stable-baselines3.readthedocs.io/en/master/ and then try some tutorials.\n",
"\n",
"----"
],
"metadata": {
"id": "qGbRDKBAHylu"
}
},
{
"cell_type": "markdown",
"source": [
"To solve this problem, we're going to use SB3 **PPO**. [PPO (aka Proximal Policy Optimization) is one of the SOTA (state of the art) Deep Reinforcement Learning algorithms that you'll study during this course](https://stable-baselines3.readthedocs.io/en/master/modules/ppo.html#example%5D).\n",
"\n",
"PPO is a combination of:\n",
"- *Value-based reinforcement learning method*: learning an action-value function that will tell us the **most valuable action to take given a state and action**.\n",
"- *Policy-based reinforcement learning method*: learning a policy that will **give us a probability distribution over actions**."
],
"metadata": {
"id": "EsOexLVcH3jd"
}
},
{
"cell_type": "markdown",
"source": [
"Stable-Baselines3 is easy to set up:\n",
"\n",
"1️⃣ You **create your environment** (in our case it was done above)\n",
"\n",
"2️⃣ You define the **model you want to use and instantiate this model** `model = PPO(\"MlpPolicy\")`\n",
"\n",
"3️⃣ You **train the agent** with `model.learn` and define the number of training timesteps\n",
"\n",
"```\n",
"# Create environment\n",
"env = gym.make('LunarLander-v2')\n",
"\n",
"# Instantiate the agent\n",
"model = PPO('MlpPolicy', env, verbose=1)\n",
"# Train the agent\n",
"model.learn(total_timesteps=int(2e5))\n",
"```"
],
"metadata": {
"id": "zcRbsX6mH7JL"
}
},
{
"cell_type": "code",
"source": [
"model = PPO(\n",
" policy = 'MlpPolicy',\n",
" env = env,\n",
" n_steps = 1024,\n",
" batch_size = 64,\n",
" n_epochs = 4,\n",
" gamma = 0.999,\n",
" gae_lambda = 0.98,\n",
" ent_coef = 0.01,\n",
" verbose=1)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "9M_BxInbHX6o",
"outputId": "6ab1336a-4dc3-41eb-d964-2f9fbddd8d1b"
},
"execution_count": 6,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Using cuda device\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"## Train the PPO agent 🏃\n",
"- Let's train our agent for 1,000,000 timesteps, don't forget to use GPU on Colab. It will take approximately ~20min, but you can use fewer timesteps if you just want to try it out.\n",
"- During the training, take a ☕ break you deserved it 🤗"
],
"metadata": {
"id": "7rEkaLL_IUs4"
}
},
{
"cell_type": "code",
"source": [
"# Train it for 1,000,000 timesteps\n",
"model.learn(total_timesteps=1000000)\n",
"# Save the model\n",
"model_name = \"ppo-LunarLander-v2\"\n",
"model.save(model_name)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "xnKCLuIEIN8m",
"outputId": "7978c997-8bf8-49b5-d23c-928ae52fe059"
},
"execution_count": 7,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"---------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 91.4 |\n",
"| ep_rew_mean | -173 |\n",
"| time/ | |\n",
"| fps | 2057 |\n",
"| iterations | 1 |\n",
"| time_elapsed | 7 |\n",
"| total_timesteps | 16384 |\n",
"---------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 95.4 |\n",
"| ep_rew_mean | -147 |\n",
"| time/ | |\n",
"| fps | 1994 |\n",
"| iterations | 2 |\n",
"| time_elapsed | 16 |\n",
"| total_timesteps | 32768 |\n",
"| train/ | |\n",
"| approx_kl | 0.008592849 |\n",
"| clip_fraction | 0.0386 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.38 |\n",
"| explained_variance | 0.000699 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 1.98e+03 |\n",
"| n_updates | 4 |\n",
"| policy_gradient_loss | -0.00511 |\n",
"| value_loss | 4.64e+03 |\n",
"-----------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 101 |\n",
"| ep_rew_mean | -131 |\n",
"| time/ | |\n",
"| fps | 1880 |\n",
"| iterations | 3 |\n",
"| time_elapsed | 26 |\n",
"| total_timesteps | 49152 |\n",
"| train/ | |\n",
"| approx_kl | 0.008314934 |\n",
"| clip_fraction | 0.0428 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.36 |\n",
"| explained_variance | -0.00236 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 882 |\n",
"| n_updates | 8 |\n",
"| policy_gradient_loss | -0.00531 |\n",
"| value_loss | 2.49e+03 |\n",
"-----------------------------------------\n",
"----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 108 |\n",
"| ep_rew_mean | -127 |\n",
"| time/ | |\n",
"| fps | 1782 |\n",
"| iterations | 4 |\n",
"| time_elapsed | 36 |\n",
"| total_timesteps | 65536 |\n",
"| train/ | |\n",
"| approx_kl | 0.00751484 |\n",
"| clip_fraction | 0.0368 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.33 |\n",
"| explained_variance | -0.0024 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 677 |\n",
"| n_updates | 12 |\n",
"| policy_gradient_loss | -0.00471 |\n",
"| value_loss | 1.42e+03 |\n",
"----------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 109 |\n",
"| ep_rew_mean | -104 |\n",
"| time/ | |\n",
"| fps | 1713 |\n",
"| iterations | 5 |\n",
"| time_elapsed | 47 |\n",
"| total_timesteps | 81920 |\n",
"| train/ | |\n",
"| approx_kl | 0.008963551 |\n",
"| clip_fraction | 0.116 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.31 |\n",
"| explained_variance | -0.000243 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 447 |\n",
"| n_updates | 16 |\n",
"| policy_gradient_loss | -0.00294 |\n",
"| value_loss | 1e+03 |\n",
"-----------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 110 |\n",
"| ep_rew_mean | -96.5 |\n",
"| time/ | |\n",
"| fps | 1704 |\n",
"| iterations | 6 |\n",
"| time_elapsed | 57 |\n",
"| total_timesteps | 98304 |\n",
"| train/ | |\n",
"| approx_kl | 0.009971031 |\n",
"| clip_fraction | 0.114 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.28 |\n",
"| explained_variance | -4.43e-05 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 216 |\n",
"| n_updates | 20 |\n",
"| policy_gradient_loss | -0.00693 |\n",
"| value_loss | 610 |\n",
"-----------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 125 |\n",
"| ep_rew_mean | -81.8 |\n",
"| time/ | |\n",
"| fps | 1662 |\n",
"| iterations | 7 |\n",
"| time_elapsed | 68 |\n",
"| total_timesteps | 114688 |\n",
"| train/ | |\n",
"| approx_kl | 0.009136068 |\n",
"| clip_fraction | 0.0764 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.28 |\n",
"| explained_variance | -5.91e-05 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 416 |\n",
"| n_updates | 24 |\n",
"| policy_gradient_loss | -0.00402 |\n",
"| value_loss | 843 |\n",
"-----------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 117 |\n",
"| ep_rew_mean | -52.1 |\n",
"| time/ | |\n",
"| fps | 1656 |\n",
"| iterations | 8 |\n",
"| time_elapsed | 79 |\n",
"| total_timesteps | 131072 |\n",
"| train/ | |\n",
"| approx_kl | 0.006604066 |\n",
"| clip_fraction | 0.0534 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.24 |\n",
"| explained_variance | 2.84e-05 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 166 |\n",
"| n_updates | 28 |\n",
"| policy_gradient_loss | -0.00503 |\n",
"| value_loss | 512 |\n",
"-----------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 124 |\n",
"| ep_rew_mean | -37.8 |\n",
"| time/ | |\n",
"| fps | 1647 |\n",
"| iterations | 9 |\n",
"| time_elapsed | 89 |\n",
"| total_timesteps | 147456 |\n",
"| train/ | |\n",
"| approx_kl | 0.0069744745 |\n",
"| clip_fraction | 0.06 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.22 |\n",
"| explained_variance | -5.65e-05 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 173 |\n",
"| n_updates | 32 |\n",
"| policy_gradient_loss | -0.00369 |\n",
"| value_loss | 421 |\n",
"------------------------------------------\n",
"----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 136 |\n",
"| ep_rew_mean | -23.8 |\n",
"| time/ | |\n",
"| fps | 1625 |\n",
"| iterations | 10 |\n",
"| time_elapsed | 100 |\n",
"| total_timesteps | 163840 |\n",
"| train/ | |\n",
"| approx_kl | 0.00981756 |\n",
"| clip_fraction | 0.0448 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.21 |\n",
"| explained_variance | 1.22e-05 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 207 |\n",
"| n_updates | 36 |\n",
"| policy_gradient_loss | -0.00282 |\n",
"| value_loss | 435 |\n",
"----------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 159 |\n",
"| ep_rew_mean | -14.5 |\n",
"| time/ | |\n",
"| fps | 1583 |\n",
"| iterations | 11 |\n",
"| time_elapsed | 113 |\n",
"| total_timesteps | 180224 |\n",
"| train/ | |\n",
"| approx_kl | 0.0049166875 |\n",
"| clip_fraction | 0.0174 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.17 |\n",
"| explained_variance | -0.000786 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 149 |\n",
"| n_updates | 40 |\n",
"| policy_gradient_loss | -0.00211 |\n",
"| value_loss | 505 |\n",
"------------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 189 |\n",
"| ep_rew_mean | -12.2 |\n",
"| time/ | |\n",
"| fps | 1486 |\n",
"| iterations | 12 |\n",
"| time_elapsed | 132 |\n",
"| total_timesteps | 196608 |\n",
"| train/ | |\n",
"| approx_kl | 0.0028343312 |\n",
"| clip_fraction | 0.0235 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.18 |\n",
"| explained_variance | 0.000166 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 172 |\n",
"| n_updates | 44 |\n",
"| policy_gradient_loss | -0.00187 |\n",
"| value_loss | 487 |\n",
"------------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 299 |\n",
"| ep_rew_mean | -6.46 |\n",
"| time/ | |\n",
"| fps | 1399 |\n",
"| iterations | 13 |\n",
"| time_elapsed | 152 |\n",
"| total_timesteps | 212992 |\n",
"| train/ | |\n",
"| approx_kl | 0.008178342 |\n",
"| clip_fraction | 0.0506 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.21 |\n",
"| explained_variance | 0.00455 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 162 |\n",
"| n_updates | 48 |\n",
"| policy_gradient_loss | -0.00297 |\n",
"| value_loss | 363 |\n",
"-----------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 356 |\n",
"| ep_rew_mean | 0.26 |\n",
"| time/ | |\n",
"| fps | 1313 |\n",
"| iterations | 14 |\n",
"| time_elapsed | 174 |\n",
"| total_timesteps | 229376 |\n",
"| train/ | |\n",
"| approx_kl | 0.0037551734 |\n",
"| clip_fraction | 0.00771 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.22 |\n",
"| explained_variance | 0.33 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 139 |\n",
"| n_updates | 52 |\n",
"| policy_gradient_loss | -0.00174 |\n",
"| value_loss | 322 |\n",
"------------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 384 |\n",
"| ep_rew_mean | 6.92 |\n",
"| time/ | |\n",
"| fps | 1238 |\n",
"| iterations | 15 |\n",
"| time_elapsed | 198 |\n",
"| total_timesteps | 245760 |\n",
"| train/ | |\n",
"| approx_kl | 0.0061729834 |\n",
"| clip_fraction | 0.0394 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.19 |\n",
"| explained_variance | 0.525 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 110 |\n",
"| n_updates | 56 |\n",
"| policy_gradient_loss | -0.00249 |\n",
"| value_loss | 273 |\n",
"------------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 460 |\n",
"| ep_rew_mean | 14.3 |\n",
"| time/ | |\n",
"| fps | 1190 |\n",
"| iterations | 16 |\n",
"| time_elapsed | 220 |\n",
"| total_timesteps | 262144 |\n",
"| train/ | |\n",
"| approx_kl | 0.0047675483 |\n",
"| clip_fraction | 0.0254 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.23 |\n",
"| explained_variance | 0.66 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 56.5 |\n",
"| n_updates | 60 |\n",
"| policy_gradient_loss | -0.00289 |\n",
"| value_loss | 212 |\n",
"------------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 518 |\n",
"| ep_rew_mean | 21.8 |\n",
"| time/ | |\n",
"| fps | 1156 |\n",
"| iterations | 17 |\n",
"| time_elapsed | 240 |\n",
"| total_timesteps | 278528 |\n",
"| train/ | |\n",
"| approx_kl | 0.0057203174 |\n",
"| clip_fraction | 0.0206 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.21 |\n",
"| explained_variance | 0.73 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 116 |\n",
"| n_updates | 64 |\n",
"| policy_gradient_loss | -0.00181 |\n",
"| value_loss | 209 |\n",
"------------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 559 |\n",
"| ep_rew_mean | 24.1 |\n",
"| time/ | |\n",
"| fps | 1118 |\n",
"| iterations | 18 |\n",
"| time_elapsed | 263 |\n",
"| total_timesteps | 294912 |\n",
"| train/ | |\n",
"| approx_kl | 0.006825205 |\n",
"| clip_fraction | 0.0734 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.18 |\n",
"| explained_variance | 0.821 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 109 |\n",
"| n_updates | 68 |\n",
"| policy_gradient_loss | -0.00244 |\n",
"| value_loss | 166 |\n",
"-----------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 583 |\n",
"| ep_rew_mean | 32.5 |\n",
"| time/ | |\n",
"| fps | 1078 |\n",
"| iterations | 19 |\n",
"| time_elapsed | 288 |\n",
"| total_timesteps | 311296 |\n",
"| train/ | |\n",
"| approx_kl | 0.005868584 |\n",
"| clip_fraction | 0.0397 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.2 |\n",
"| explained_variance | 0.853 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 70.1 |\n",
"| n_updates | 72 |\n",
"| policy_gradient_loss | -0.00224 |\n",
"| value_loss | 106 |\n",
"-----------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 649 |\n",
"| ep_rew_mean | 45.6 |\n",
"| time/ | |\n",
"| fps | 1043 |\n",
"| iterations | 20 |\n",
"| time_elapsed | 314 |\n",
"| total_timesteps | 327680 |\n",
"| train/ | |\n",
"| approx_kl | 0.0054366277 |\n",
"| clip_fraction | 0.0382 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.18 |\n",
"| explained_variance | 0.796 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 103 |\n",
"| n_updates | 76 |\n",
"| policy_gradient_loss | -0.00313 |\n",
"| value_loss | 182 |\n",
"------------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 721 |\n",
"| ep_rew_mean | 58.4 |\n",
"| time/ | |\n",
"| fps | 1010 |\n",
"| iterations | 21 |\n",
"| time_elapsed | 340 |\n",
"| total_timesteps | 344064 |\n",
"| train/ | |\n",
"| approx_kl | 0.004255467 |\n",
"| clip_fraction | 0.0282 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.18 |\n",
"| explained_variance | 0.901 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 22.7 |\n",
"| n_updates | 80 |\n",
"| policy_gradient_loss | -0.00119 |\n",
"| value_loss | 74.4 |\n",
"-----------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 784 |\n",
"| ep_rew_mean | 62.6 |\n",
"| time/ | |\n",
"| fps | 981 |\n",
"| iterations | 22 |\n",
"| time_elapsed | 367 |\n",
"| total_timesteps | 360448 |\n",
"| train/ | |\n",
"| approx_kl | 0.0045252834 |\n",
"| clip_fraction | 0.0338 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.14 |\n",
"| explained_variance | 0.926 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 18.7 |\n",
"| n_updates | 84 |\n",
"| policy_gradient_loss | -0.00135 |\n",
"| value_loss | 54.4 |\n",
"------------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 766 |\n",
"| ep_rew_mean | 63.5 |\n",
"| time/ | |\n",
"| fps | 964 |\n",
"| iterations | 23 |\n",
"| time_elapsed | 390 |\n",
"| total_timesteps | 376832 |\n",
"| train/ | |\n",
"| approx_kl | 0.0060958676 |\n",
"| clip_fraction | 0.0592 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.11 |\n",
"| explained_variance | 0.886 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 10.6 |\n",
"| n_updates | 88 |\n",
"| policy_gradient_loss | -0.00281 |\n",
"| value_loss | 84.6 |\n",
"------------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 770 |\n",
"| ep_rew_mean | 66.4 |\n",
"| time/ | |\n",
"| fps | 948 |\n",
"| iterations | 24 |\n",
"| time_elapsed | 414 |\n",
"| total_timesteps | 393216 |\n",
"| train/ | |\n",
"| approx_kl | 0.004979129 |\n",
"| clip_fraction | 0.0494 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.08 |\n",
"| explained_variance | 0.877 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 103 |\n",
"| n_updates | 92 |\n",
"| policy_gradient_loss | -0.0019 |\n",
"| value_loss | 129 |\n",
"-----------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 720 |\n",
"| ep_rew_mean | 63.6 |\n",
"| time/ | |\n",
"| fps | 932 |\n",
"| iterations | 25 |\n",
"| time_elapsed | 439 |\n",
"| total_timesteps | 409600 |\n",
"| train/ | |\n",
"| approx_kl | 0.006599961 |\n",
"| clip_fraction | 0.0355 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.06 |\n",
"| explained_variance | 0.889 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 30.4 |\n",
"| n_updates | 96 |\n",
"| policy_gradient_loss | -0.000833 |\n",
"| value_loss | 126 |\n",
"-----------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 684 |\n",
"| ep_rew_mean | 69.2 |\n",
"| time/ | |\n",
"| fps | 922 |\n",
"| iterations | 26 |\n",
"| time_elapsed | 461 |\n",
"| total_timesteps | 425984 |\n",
"| train/ | |\n",
"| approx_kl | 0.0058977026 |\n",
"| clip_fraction | 0.0418 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.06 |\n",
"| explained_variance | 0.858 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 166 |\n",
"| n_updates | 100 |\n",
"| policy_gradient_loss | -0.00285 |\n",
"| value_loss | 135 |\n",
"------------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 711 |\n",
"| ep_rew_mean | 81 |\n",
"| time/ | |\n",
"| fps | 911 |\n",
"| iterations | 27 |\n",
"| time_elapsed | 485 |\n",
"| total_timesteps | 442368 |\n",
"| train/ | |\n",
"| approx_kl | 0.005546063 |\n",
"| clip_fraction | 0.0259 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.05 |\n",
"| explained_variance | 0.882 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 61.7 |\n",
"| n_updates | 104 |\n",
"| policy_gradient_loss | -0.000982 |\n",
"| value_loss | 128 |\n",
"-----------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 708 |\n",
"| ep_rew_mean | 85.6 |\n",
"| time/ | |\n",
"| fps | 901 |\n",
"| iterations | 28 |\n",
"| time_elapsed | 508 |\n",
"| total_timesteps | 458752 |\n",
"| train/ | |\n",
"| approx_kl | 0.005223057 |\n",
"| clip_fraction | 0.056 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.01 |\n",
"| explained_variance | 0.871 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 13.2 |\n",
"| n_updates | 108 |\n",
"| policy_gradient_loss | -0.000185 |\n",
"| value_loss | 109 |\n",
"-----------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 721 |\n",
"| ep_rew_mean | 92.1 |\n",
"| time/ | |\n",
"| fps | 896 |\n",
"| iterations | 29 |\n",
"| time_elapsed | 529 |\n",
"| total_timesteps | 475136 |\n",
"| train/ | |\n",
"| approx_kl | 0.0037519943 |\n",
"| clip_fraction | 0.0358 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.03 |\n",
"| explained_variance | 0.873 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 139 |\n",
"| n_updates | 112 |\n",
"| policy_gradient_loss | -0.000845 |\n",
"| value_loss | 113 |\n",
"------------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 737 |\n",
"| ep_rew_mean | 95.9 |\n",
"| time/ | |\n",
"| fps | 885 |\n",
"| iterations | 30 |\n",
"| time_elapsed | 554 |\n",
"| total_timesteps | 491520 |\n",
"| train/ | |\n",
"| approx_kl | 0.0069649937 |\n",
"| clip_fraction | 0.0464 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.03 |\n",
"| explained_variance | 0.856 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 52.4 |\n",
"| n_updates | 116 |\n",
"| policy_gradient_loss | -0.000394 |\n",
"| value_loss | 137 |\n",
"------------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 761 |\n",
"| ep_rew_mean | 99.7 |\n",
"| time/ | |\n",
"| fps | 877 |\n",
"| iterations | 31 |\n",
"| time_elapsed | 579 |\n",
"| total_timesteps | 507904 |\n",
"| train/ | |\n",
"| approx_kl | 0.0041906065 |\n",
"| clip_fraction | 0.0287 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.02 |\n",
"| explained_variance | 0.88 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 159 |\n",
"| n_updates | 120 |\n",
"| policy_gradient_loss | -0.000867 |\n",
"| value_loss | 104 |\n",
"------------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 759 |\n",
"| ep_rew_mean | 96.8 |\n",
"| time/ | |\n",
"| fps | 867 |\n",
"| iterations | 32 |\n",
"| time_elapsed | 604 |\n",
"| total_timesteps | 524288 |\n",
"| train/ | |\n",
"| approx_kl | 0.0038534352 |\n",
"| clip_fraction | 0.0332 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.05 |\n",
"| explained_variance | 0.919 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 45 |\n",
"| n_updates | 124 |\n",
"| policy_gradient_loss | 1.87e-05 |\n",
"| value_loss | 70.1 |\n",
"------------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 783 |\n",
"| ep_rew_mean | 100 |\n",
"| time/ | |\n",
"| fps | 861 |\n",
"| iterations | 33 |\n",
"| time_elapsed | 627 |\n",
"| total_timesteps | 540672 |\n",
"| train/ | |\n",
"| approx_kl | 0.0050528254 |\n",
"| clip_fraction | 0.0399 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.07 |\n",
"| explained_variance | 0.929 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 34.5 |\n",
"| n_updates | 128 |\n",
"| policy_gradient_loss | -0.000154 |\n",
"| value_loss | 71.6 |\n",
"------------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 820 |\n",
"| ep_rew_mean | 104 |\n",
"| time/ | |\n",
"| fps | 855 |\n",
"| iterations | 34 |\n",
"| time_elapsed | 651 |\n",
"| total_timesteps | 557056 |\n",
"| train/ | |\n",
"| approx_kl | 0.0059309453 |\n",
"| clip_fraction | 0.0369 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.06 |\n",
"| explained_variance | 0.948 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 10.9 |\n",
"| n_updates | 132 |\n",
"| policy_gradient_loss | -0.000717 |\n",
"| value_loss | 54.9 |\n",
"------------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 848 |\n",
"| ep_rew_mean | 108 |\n",
"| time/ | |\n",
"| fps | 846 |\n",
"| iterations | 35 |\n",
"| time_elapsed | 677 |\n",
"| total_timesteps | 573440 |\n",
"| train/ | |\n",
"| approx_kl | 0.0054781875 |\n",
"| clip_fraction | 0.0353 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.04 |\n",
"| explained_variance | 0.97 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 13 |\n",
"| n_updates | 136 |\n",
"| policy_gradient_loss | -0.000663 |\n",
"| value_loss | 27.4 |\n",
"------------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 880 |\n",
"| ep_rew_mean | 115 |\n",
"| time/ | |\n",
"| fps | 836 |\n",
"| iterations | 36 |\n",
"| time_elapsed | 704 |\n",
"| total_timesteps | 589824 |\n",
"| train/ | |\n",
"| approx_kl | 0.005830043 |\n",
"| clip_fraction | 0.0461 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.1 |\n",
"| explained_variance | 0.971 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 3.07 |\n",
"| n_updates | 140 |\n",
"| policy_gradient_loss | -8.33e-05 |\n",
"| value_loss | 25.5 |\n",
"-----------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 902 |\n",
"| ep_rew_mean | 116 |\n",
"| time/ | |\n",
"| fps | 828 |\n",
"| iterations | 37 |\n",
"| time_elapsed | 731 |\n",
"| total_timesteps | 606208 |\n",
"| train/ | |\n",
"| approx_kl | 0.006710346 |\n",
"| clip_fraction | 0.038 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.09 |\n",
"| explained_variance | 0.979 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 18.3 |\n",
"| n_updates | 144 |\n",
"| policy_gradient_loss | -0.000692 |\n",
"| value_loss | 22.1 |\n",
"-----------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 924 |\n",
"| ep_rew_mean | 121 |\n",
"| time/ | |\n",
"| fps | 821 |\n",
"| iterations | 38 |\n",
"| time_elapsed | 757 |\n",
"| total_timesteps | 622592 |\n",
"| train/ | |\n",
"| approx_kl | 0.005125195 |\n",
"| clip_fraction | 0.0336 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.09 |\n",
"| explained_variance | 0.986 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 3.32 |\n",
"| n_updates | 148 |\n",
"| policy_gradient_loss | -0.000416 |\n",
"| value_loss | 14.4 |\n",
"-----------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 946 |\n",
"| ep_rew_mean | 127 |\n",
"| time/ | |\n",
"| fps | 815 |\n",
"| iterations | 39 |\n",
"| time_elapsed | 783 |\n",
"| total_timesteps | 638976 |\n",
"| train/ | |\n",
"| approx_kl | 0.005139123 |\n",
"| clip_fraction | 0.0434 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.08 |\n",
"| explained_variance | 0.973 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 12.8 |\n",
"| n_updates | 152 |\n",
"| policy_gradient_loss | -0.00122 |\n",
"| value_loss | 32.2 |\n",
"-----------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 961 |\n",
"| ep_rew_mean | 130 |\n",
"| time/ | |\n",
"| fps | 811 |\n",
"| iterations | 40 |\n",
"| time_elapsed | 807 |\n",
"| total_timesteps | 655360 |\n",
"| train/ | |\n",
"| approx_kl | 0.009937766 |\n",
"| clip_fraction | 0.0721 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.06 |\n",
"| explained_variance | 0.994 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 4.59 |\n",
"| n_updates | 156 |\n",
"| policy_gradient_loss | -0.00251 |\n",
"| value_loss | 5.8 |\n",
"-----------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 949 |\n",
"| ep_rew_mean | 128 |\n",
"| time/ | |\n",
"| fps | 807 |\n",
"| iterations | 41 |\n",
"| time_elapsed | 831 |\n",
"| total_timesteps | 671744 |\n",
"| train/ | |\n",
"| approx_kl | 0.005214632 |\n",
"| clip_fraction | 0.0342 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.02 |\n",
"| explained_variance | 0.993 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 4.09 |\n",
"| n_updates | 160 |\n",
"| policy_gradient_loss | -0.00183 |\n",
"| value_loss | 6.35 |\n",
"-----------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 926 |\n",
"| ep_rew_mean | 125 |\n",
"| time/ | |\n",
"| fps | 804 |\n",
"| iterations | 42 |\n",
"| time_elapsed | 854 |\n",
"| total_timesteps | 688128 |\n",
"| train/ | |\n",
"| approx_kl | 0.003999071 |\n",
"| clip_fraction | 0.027 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -1.03 |\n",
"| explained_variance | 0.971 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 17.9 |\n",
"| n_updates | 164 |\n",
"| policy_gradient_loss | -0.000946 |\n",
"| value_loss | 35.9 |\n",
"-----------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 926 |\n",
"| ep_rew_mean | 128 |\n",
"| time/ | |\n",
"| fps | 801 |\n",
"| iterations | 43 |\n",
"| time_elapsed | 879 |\n",
"| total_timesteps | 704512 |\n",
"| train/ | |\n",
"| approx_kl | 0.0034697542 |\n",
"| clip_fraction | 0.0162 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -0.984 |\n",
"| explained_variance | 0.961 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 34 |\n",
"| n_updates | 168 |\n",
"| policy_gradient_loss | -0.00188 |\n",
"| value_loss | 53.1 |\n",
"------------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 933 |\n",
"| ep_rew_mean | 129 |\n",
"| time/ | |\n",
"| fps | 798 |\n",
"| iterations | 44 |\n",
"| time_elapsed | 902 |\n",
"| total_timesteps | 720896 |\n",
"| train/ | |\n",
"| approx_kl | 0.0065774596 |\n",
"| clip_fraction | 0.0568 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -0.992 |\n",
"| explained_variance | 0.995 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 0.887 |\n",
"| n_updates | 172 |\n",
"| policy_gradient_loss | -0.000302 |\n",
"| value_loss | 4.7 |\n",
"------------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 933 |\n",
"| ep_rew_mean | 131 |\n",
"| time/ | |\n",
"| fps | 797 |\n",
"| iterations | 45 |\n",
"| time_elapsed | 925 |\n",
"| total_timesteps | 737280 |\n",
"| train/ | |\n",
"| approx_kl | 0.0046285056 |\n",
"| clip_fraction | 0.0328 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -0.97 |\n",
"| explained_variance | 0.989 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 1.37 |\n",
"| n_updates | 176 |\n",
"| policy_gradient_loss | -0.000609 |\n",
"| value_loss | 13.4 |\n",
"------------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 911 |\n",
"| ep_rew_mean | 130 |\n",
"| time/ | |\n",
"| fps | 796 |\n",
"| iterations | 46 |\n",
"| time_elapsed | 946 |\n",
"| total_timesteps | 753664 |\n",
"| train/ | |\n",
"| approx_kl | 0.0037862058 |\n",
"| clip_fraction | 0.0439 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -0.946 |\n",
"| explained_variance | 0.996 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 3.77 |\n",
"| n_updates | 180 |\n",
"| policy_gradient_loss | -0.000404 |\n",
"| value_loss | 3.67 |\n",
"------------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 940 |\n",
"| ep_rew_mean | 135 |\n",
"| time/ | |\n",
"| fps | 790 |\n",
"| iterations | 47 |\n",
"| time_elapsed | 974 |\n",
"| total_timesteps | 770048 |\n",
"| train/ | |\n",
"| approx_kl | 0.0054154107 |\n",
"| clip_fraction | 0.0214 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -0.935 |\n",
"| explained_variance | 0.967 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 11 |\n",
"| n_updates | 184 |\n",
"| policy_gradient_loss | -0.000244 |\n",
"| value_loss | 44.4 |\n",
"------------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 963 |\n",
"| ep_rew_mean | 139 |\n",
"| time/ | |\n",
"| fps | 788 |\n",
"| iterations | 48 |\n",
"| time_elapsed | 997 |\n",
"| total_timesteps | 786432 |\n",
"| train/ | |\n",
"| approx_kl | 0.0031047282 |\n",
"| clip_fraction | 0.0409 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -0.931 |\n",
"| explained_variance | 0.995 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 0.88 |\n",
"| n_updates | 188 |\n",
"| policy_gradient_loss | -0.000506 |\n",
"| value_loss | 3.54 |\n",
"------------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 963 |\n",
"| ep_rew_mean | 140 |\n",
"| time/ | |\n",
"| fps | 784 |\n",
"| iterations | 49 |\n",
"| time_elapsed | 1023 |\n",
"| total_timesteps | 802816 |\n",
"| train/ | |\n",
"| approx_kl | 0.0055639897 |\n",
"| clip_fraction | 0.036 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -0.929 |\n",
"| explained_variance | 0.997 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 1.05 |\n",
"| n_updates | 192 |\n",
"| policy_gradient_loss | -0.000335 |\n",
"| value_loss | 3.08 |\n",
"------------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 963 |\n",
"| ep_rew_mean | 141 |\n",
"| time/ | |\n",
"| fps | 783 |\n",
"| iterations | 50 |\n",
"| time_elapsed | 1046 |\n",
"| total_timesteps | 819200 |\n",
"| train/ | |\n",
"| approx_kl | 0.004088245 |\n",
"| clip_fraction | 0.0379 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -0.922 |\n",
"| explained_variance | 0.998 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 0.566 |\n",
"| n_updates | 196 |\n",
"| policy_gradient_loss | -0.000669 |\n",
"| value_loss | 2.59 |\n",
"-----------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 963 |\n",
"| ep_rew_mean | 141 |\n",
"| time/ | |\n",
"| fps | 781 |\n",
"| iterations | 51 |\n",
"| time_elapsed | 1069 |\n",
"| total_timesteps | 835584 |\n",
"| train/ | |\n",
"| approx_kl | 0.005680429 |\n",
"| clip_fraction | 0.0512 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -0.903 |\n",
"| explained_variance | 0.988 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 1.16 |\n",
"| n_updates | 200 |\n",
"| policy_gradient_loss | -0.000512 |\n",
"| value_loss | 14.4 |\n",
"-----------------------------------------\n",
"---------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 971 |\n",
"| ep_rew_mean | 143 |\n",
"| time/ | |\n",
"| fps | 779 |\n",
"| iterations | 52 |\n",
"| time_elapsed | 1093 |\n",
"| total_timesteps | 851968 |\n",
"| train/ | |\n",
"| approx_kl | 0.0044502 |\n",
"| clip_fraction | 0.0415 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -0.878 |\n",
"| explained_variance | 0.998 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 0.71 |\n",
"| n_updates | 204 |\n",
"| policy_gradient_loss | -0.000632 |\n",
"| value_loss | 1.83 |\n",
"---------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 942 |\n",
"| ep_rew_mean | 141 |\n",
"| time/ | |\n",
"| fps | 778 |\n",
"| iterations | 53 |\n",
"| time_elapsed | 1115 |\n",
"| total_timesteps | 868352 |\n",
"| train/ | |\n",
"| approx_kl | 0.0034386532 |\n",
"| clip_fraction | 0.0164 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -0.867 |\n",
"| explained_variance | 0.974 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 13.9 |\n",
"| n_updates | 208 |\n",
"| policy_gradient_loss | -0.000543 |\n",
"| value_loss | 34.8 |\n",
"------------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 935 |\n",
"| ep_rew_mean | 142 |\n",
"| time/ | |\n",
"| fps | 776 |\n",
"| iterations | 54 |\n",
"| time_elapsed | 1138 |\n",
"| total_timesteps | 884736 |\n",
"| train/ | |\n",
"| approx_kl | 0.0028421837 |\n",
"| clip_fraction | 0.0172 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -0.841 |\n",
"| explained_variance | 0.964 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 4.44 |\n",
"| n_updates | 212 |\n",
"| policy_gradient_loss | -0.000334 |\n",
"| value_loss | 55.6 |\n",
"------------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 897 |\n",
"| ep_rew_mean | 138 |\n",
"| time/ | |\n",
"| fps | 776 |\n",
"| iterations | 55 |\n",
"| time_elapsed | 1160 |\n",
"| total_timesteps | 901120 |\n",
"| train/ | |\n",
"| approx_kl | 0.0049287863 |\n",
"| clip_fraction | 0.0509 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -0.836 |\n",
"| explained_variance | 0.989 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 1.5 |\n",
"| n_updates | 216 |\n",
"| policy_gradient_loss | -0.000409 |\n",
"| value_loss | 16.1 |\n",
"------------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 867 |\n",
"| ep_rew_mean | 137 |\n",
"| time/ | |\n",
"| fps | 775 |\n",
"| iterations | 56 |\n",
"| time_elapsed | 1183 |\n",
"| total_timesteps | 917504 |\n",
"| train/ | |\n",
"| approx_kl | 0.0024348623 |\n",
"| clip_fraction | 0.0192 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -0.828 |\n",
"| explained_variance | 0.964 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 1.73 |\n",
"| n_updates | 220 |\n",
"| policy_gradient_loss | -9.98e-05 |\n",
"| value_loss | 46.9 |\n",
"------------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 842 |\n",
"| ep_rew_mean | 139 |\n",
"| time/ | |\n",
"| fps | 775 |\n",
"| iterations | 57 |\n",
"| time_elapsed | 1204 |\n",
"| total_timesteps | 933888 |\n",
"| train/ | |\n",
"| approx_kl | 0.004851416 |\n",
"| clip_fraction | 0.0385 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -0.844 |\n",
"| explained_variance | 0.957 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 40.2 |\n",
"| n_updates | 224 |\n",
"| policy_gradient_loss | -0.000544 |\n",
"| value_loss | 68.5 |\n",
"-----------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 810 |\n",
"| ep_rew_mean | 142 |\n",
"| time/ | |\n",
"| fps | 775 |\n",
"| iterations | 58 |\n",
"| time_elapsed | 1225 |\n",
"| total_timesteps | 950272 |\n",
"| train/ | |\n",
"| approx_kl | 0.0043038856 |\n",
"| clip_fraction | 0.0455 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -0.788 |\n",
"| explained_variance | 0.936 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 52.5 |\n",
"| n_updates | 228 |\n",
"| policy_gradient_loss | -0.000662 |\n",
"| value_loss | 99.8 |\n",
"------------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 720 |\n",
"| ep_rew_mean | 153 |\n",
"| time/ | |\n",
"| fps | 776 |\n",
"| iterations | 59 |\n",
"| time_elapsed | 1244 |\n",
"| total_timesteps | 966656 |\n",
"| train/ | |\n",
"| approx_kl | 0.006026829 |\n",
"| clip_fraction | 0.0867 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -0.716 |\n",
"| explained_variance | 0.866 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 24.9 |\n",
"| n_updates | 232 |\n",
"| policy_gradient_loss | -0.0025 |\n",
"| value_loss | 197 |\n",
"-----------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 608 |\n",
"| ep_rew_mean | 175 |\n",
"| time/ | |\n",
"| fps | 778 |\n",
"| iterations | 60 |\n",
"| time_elapsed | 1262 |\n",
"| total_timesteps | 983040 |\n",
"| train/ | |\n",
"| approx_kl | 0.004601596 |\n",
"| clip_fraction | 0.0711 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -0.696 |\n",
"| explained_variance | 0.814 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 188 |\n",
"| n_updates | 236 |\n",
"| policy_gradient_loss | -0.00272 |\n",
"| value_loss | 317 |\n",
"-----------------------------------------\n",
"-----------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 481 |\n",
"| ep_rew_mean | 207 |\n",
"| time/ | |\n",
"| fps | 781 |\n",
"| iterations | 61 |\n",
"| time_elapsed | 1278 |\n",
"| total_timesteps | 999424 |\n",
"| train/ | |\n",
"| approx_kl | 0.006298151 |\n",
"| clip_fraction | 0.0434 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -0.763 |\n",
"| explained_variance | 0.779 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 124 |\n",
"| n_updates | 240 |\n",
"| policy_gradient_loss | -0.00223 |\n",
"| value_loss | 341 |\n",
"-----------------------------------------\n",
"------------------------------------------\n",
"| rollout/ | |\n",
"| ep_len_mean | 405 |\n",
"| ep_rew_mean | 216 |\n",
"| time/ | |\n",
"| fps | 784 |\n",
"| iterations | 62 |\n",
"| time_elapsed | 1294 |\n",
"| total_timesteps | 1015808 |\n",
"| train/ | |\n",
"| approx_kl | 0.0059260186 |\n",
"| clip_fraction | 0.0571 |\n",
"| clip_range | 0.2 |\n",
"| entropy_loss | -0.745 |\n",
"| explained_variance | 0.702 |\n",
"| learning_rate | 0.0003 |\n",
"| loss | 79.2 |\n",
"| n_updates | 244 |\n",
"| policy_gradient_loss | -0.00215 |\n",
"| value_loss | 322 |\n",
"------------------------------------------\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"## Evaluate the agent 📈\n",
"- Remember to wrap the environment in a [Monitor](https://stable-baselines3.readthedocs.io/en/master/common/monitor.html).\n",
"- Now that our Lunar Lander agent is trained 🚀, we need to **check its performance**.\n",
"- Stable-Baselines3 provides a method to do that: `evaluate_policy`.\n",
"- To fill that part you need to [check the documentation](https://stable-baselines3.readthedocs.io/en/master/guide/examples.html#basic-usage-training-saving-loading)\n",
"- In the next step, we'll see **how to automatically evaluate and share your agent to compete in a leaderboard, but for now let's do it ourselves**\n",
"\n",
"\n",
"💡 When you evaluate your agent, you should not use your training environment but create an evaluation environment."
],
"metadata": {
"id": "jviXp38AI8V2"
}
},
{
"cell_type": "code",
"source": [
"#@title\n",
"eval_env = Monitor(gym.make(\"LunarLander-v2\"))\n",
"mean_reward, std_reward = evaluate_policy(model, eval_env, n_eval_episodes=10, deterministic=True)\n",
"print(f\"mean_reward={mean_reward:.2f} +/- {std_reward}\")"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "9-5iUlFVIzg_",
"outputId": "a6f74e67-54f3-4c9f-ba8d-608ebd7caf89"
},
"execution_count": 8,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"mean_reward=257.92 +/- 19.23536582855511\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": [
"96ab2b48ede34f369b6eae8d3473897f",
"e8d79186fcdc4ef0868c833180761f62",
"138e17534b7c4f6d84473fffd6f88bd7",
"1a4e0cd0133548d992e6c5adebe90aa0",
"1e46fd051f2243fa839124f4ede1e9f3",
"85b97b194f5746c5a2cfb85421bf7cfb",
"8d86630525dc4b39aafb8074d2e262b0",
"a81c5bf9a5e344368cc1b942708bdb63",
"37770393ceda4ec89408f749b4159606",
"6e230407612c4722bf2df2f9a55d241d",
"68d93ffd427d4b88b6200c3b2988f7f5",
"78115d3432584e26a3b9732f23529d4c",
"66ff63784e49429098363abe06af82ab",
"2c2fdc4bb2304afaa257093dfd5e9214",
"901b2ed4d68341acb17f85a38931f02e",
"a2262b9caf1041e6adf8121716d1b32b",
"a551515ddf7c4c6fac9d7bc5737cc4bb",
"550b83b4923d493d85733e903e7ffd01",
"a64d097488804935a75f26a05b33c666",
"4ad9891b73f74bedbcb59824f12bd7ee",
"17fbbdd9e0444ef7b20842c3cc59b345",
"864e1e7bcc4b430eba7ba686376c0e8a",
"e8707d8c9ffd4a22a273a702b8e1e316",
"ca7d6f64d2c545438d40731b9f955159",
"6df7400442be4771b3d84d9428a9b908",
"5a604c84e40e4b8c94b113ec9261e327",
"ff5158df6e7348cdb3f240943502a03f",
"87532f73bbc24354a95c28f1ba44f453",
"ef04a55379e449ac97b916089e84b0da",
"ad83925317804af3ba2f427c6ce33d66",
"bb37f4b335f84236bf76040a99a3c66b",
"8fb75f60269045929b86a00599724e94"
]
},
"id": "yYPMH6SpJE74",
"outputId": "669da289-79f1-49e7-f19a-38068e718b36"
},
"execution_count": 9,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"VBox(children=(HTML(value=' "
],
"metadata": {
"id": "yVRePytvQ7Wa"
}
},
{
"cell_type": "code",
"source": [
"!pip install -Uqqq shimmy"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "GmrpLp4aQ8C-",
"outputId": "8eb98988-2b18-491e-dc01-92216f1c060a"
},
"execution_count": 11,
"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": "code",
"source": [
"from huggingface_sb3 import load_from_hub\n",
"repo_id = \"Classroom-workshop/assignment2-omar\" # The repo_id\n",
"filename = \"ppo-LunarLander-v2.zip\" # The model filename.zip\n",
"\n",
"# When the model was trained on Python 3.8 the pickle protocol is 5\n",
"# But Python 3.6, 3.7 use protocol 4\n",
"# In order to get compatibility we need to:\n",
"# 1. Install pickle5 (we done it at the beginning of the colab)\n",
"# 2. Create a custom empty object we pass as parameter to PPO.load()\n",
"custom_objects = {\n",
" \"learning_rate\": 0.0,\n",
" \"lr_schedule\": lambda _: 0.0,\n",
" \"clip_range\": lambda _: 0.0,\n",
"}\n",
"\n",
"checkpoint = load_from_hub(repo_id, filename)\n",
"model = PPO.load(checkpoint, custom_objects=custom_objects, print_system_info=True)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 462,
"referenced_widgets": [
"40483e1b5a9e47928fa5787e7f52f486",
"35baae5e2c7f49949ccb9b4298ddce39",
"dc06c86c0acd41ca8616c76e55dfeb55",
"c386ac68558c4598a32e01a7eec835b1",
"c37d97a3fa9a465abfc13ca97bb01709",
"4e860d0d9c0e439b81373f8c70c45d4a",
"1f70bb1afe25415f8c7bfd42222b579b",
"98d25a66d61147db875af377a4fc2070",
"1ef8cea9ecb74bf38ea2763933d2a69d",
"2e9cc7b9bd3a4e5f8e6b85ac2aa51f9e",
"5e62fef035f34dfdb0a8865ba3ea85c7"
]
},
"id": "C-OQfVmsRAls",
"outputId": "a1be0366-6336-4249-8d5f-016a065d5eae"
},
"execution_count": 12,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"Downloading ppo-LunarLander-v2.zip: 0%| | 0.00/146k [00:00