Test commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 500.00 +/- 0.00
+      value: 9.80 +/- 0.60
       name: mean_reward
       verified: false
 ---

a2c_Cart_Pole.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08fc3afe574e197c4fe2d6c51ae6933106c50693c82a014466d343f605bc545b
-size 93705
+oid sha256:f387f56222466c1691aa9909b225448792f713c9299113eecd0f97555ce0ac95
+size 93677

a2c_Cart_Pole/data

@@ -4,20 +4,20 @@
         ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
         "__module__": "stable_baselines3.common.policies",
         "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ",
-        "__init__": "<function ActorCriticPolicy.__init__ at 0x00000234F67A4310>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x00000234F67A43A0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x00000234F67A4430>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x00000234F67A44C0>",
-        "_build": "<function ActorCriticPolicy._build at 0x00000234F67A4550>",
-        "forward": "<function ActorCriticPolicy.forward at 0x00000234F67A45E0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x00000234F67A4670>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x00000234F67A4700>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x00000234F67A4790>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x00000234F67A4820>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x00000234F67A48B0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x00000234F67A4940>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x000002925CA78AF0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000002925CA78B80>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000002925CA78C10>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000002925CA78CA0>",
+        "_build": "<function ActorCriticPolicy._build at 0x000002925CA78D30>",
+        "forward": "<function ActorCriticPolicy.forward at 0x000002925CA78DC0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x000002925CA78E50>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000002925CA78EE0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x000002925CA78F70>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000002925CA79000>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000002925CA79090>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x000002925CA79120>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x00000234F67A0FC0>"
+        "_abc_impl": "<_abc._abc_data object at 0x000002925CA71D40>"
     },
     "verbose": 1,
     "policy_kwargs": {
@@ -57,16 +57,16 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1676199912094791500,
+    "start_time": 1676202537295446500,
     "learning_rate": 0.0007,
-    "tensorboard_log": "runs/dcbpn4e8",
+    "tensorboard_log": "runs/mcfwzfhs",
     "lr_schedule": {
         ":type:": "<class 'function'>",
         ":serialized:": "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"
     },
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAIPyQD4PnwW/LEcWvvQt+LyUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"
+        ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAP/fnL1hcm+/aH4LPYzjtD+UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -79,7 +79,7 @@
     "_current_progress_remaining": 0.0,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "gAWV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQFeAAAAAAACMAWyUS16MAXSUR0A1ttU4rBj4dX2UKGgGR0BAgAAAAAAAaAdLIWgIR0A1veZof0VadX2UKGgGR0BcwAAAAAAAaAdLc2gIR0A13Fy7wrlOdX2UKGgGR0BCAAAAAAAAaAdLJGgIR0A15sv7FbV0dX2UKGgGR0BZAAAAAAAAaAdLZGgIR0A2AWac7QsxdX2UKGgGR0A6AAAAAAAAaAdLGmgIR0A2CG+sYEW7dX2UKGgGR0A4AAAAAAAAaAdLGGgIR0A2DuQ6p5u7dX2UKGgGR0A7AAAAAAAAaAdLG2gIR0A2FliBoVVQdX2UKGgGR0A2AAAAAAAAaAdLFmgIR0A2IbRWtEG8dX2UKGgGR0BDAAAAAAAAaAdLJmgIR0A2KtapxWDIdX2UKGgGR0AwAAAAAAAAaAdLEGgIR0A2LvX9R77bdX2UKGgGR0A3AAAAAAAAaAdLF2gIR0A2NiD/VAiWdX2UKGgGR0A8AAAAAAAAaAdLHGgIR0A2PVuJk5IZdX2UKGgGR0AuAAAAAAAAaAdLD2gIR0A2QTKT0QK8dX2UKGgGR0AqAAAAAAAAaAdLDWgIR0A2Q9l2/zredX2UKGgGR0AuAAAAAAAAaAdLD2gIR0A2SAlOXVsldX2UKGgGR0AzAAAAAAAAaAdLE2gIR0A2TbcoH9m6dX2UKGgGR0AmAAAAAAAAaAdLC2gIR0A2UM2m51/2dX2UKGgGR0AyAAAAAAAAaAdLEmgIR0A2VbN8ma6SdX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A2V/8l5WzXdX2UKGgGR0AmAAAAAAAAaAdLC2gIR0A2WvECNjsldX2UKGgGR0AoAAAAAAAAaAdLDGgIR0A2XcOby6MBdX2UKGgGR0AoAAAAAAAAaAdLDGgIR0A2Ya4MF2V3dX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A2ZHoouwotdX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A2ZwmE4//vdX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A2aX3xnWaudX2UKGgGR0AoAAAAAAAAaAdLDGgIR0A2bJBgNPP+dX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A2b2lVLi++dX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A2cdc0Ltu2dX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A2c9kjHGS7dX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A2dndweeWfdX2UKGgGR0AgAAAAAAAAaAdLCGgIR0A2eGd7OVxCdX2UKGgGR0AgAAAAAAAAaAdLCGgIR0A2efb9If8udX2UKGgGR0AgAAAAAAAAaAdLCGgIR0A2fAu7HyVfdX2UKGgGR0AmAAAAAAAAaAdLC2gIR0A2fij+JgstdX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A2gEZzgdfcdX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A2gvIfbKzSdX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A2hUXYUWVNdX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A2h5O8CgbqdX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A2ie2d/axpdX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A2jMTN+so2dX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A2j76YVqN7dX2UKGgGR0AmAAAAAAAAaAdLC2gIR0A2ko/A0sOHdX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A2lWCmMwUQdX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A2l/Aj6eoUdX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A2mn9vS+g2dX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A2nVARkEs8dX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A2n77sOXmedX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A2ofICEHt4dX2UKGgGR0AgAAAAAAAAaAdLCGgIR0A2qQYk3S8bdX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A2qtdiUgSwdX2UKGgGR0AmAAAAAAAAaAdLC2gIR0A2rfTkQwsYdX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A2s5a/yoXLdX2UKGgGR0AmAAAAAAAAaAdLC2gIR0A2t23KB/ZvdX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A2ut0FKTStdX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A2vhP0qYqodX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A2wG6wt8NQdX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A2ww+dK/VRdX2UKGgGR0AqAAAAAAAAaAdLDWgIR0A2xuYx+KCQdX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A2yG+bmU4adX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A2yn+hoM8YdX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A2zM6zVtoBdX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A2z3X7Lt/ndX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A20gbIcR16dX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A21G5+YtxudX2UKGgGR0AoAAAAAAAAaAdLDGgIR0A22HBDXvphdX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A22wI+nqFAdX2UKGgGR0AmAAAAAAAAaAdLC2gIR0A23fg75mAcdX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A24J4B3iaRdX2UKGgGR0AqAAAAAAAAaAdLDWgIR0A244KhL5ARdX2UKGgGR0AmAAAAAAAAaAdLC2gIR0A25jurp7kXdX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A26J79hqj8dX2UKGgGR0AgAAAAAAAAaAdLCGgIR0A26sbedkJ8dX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A27SJCSidrdX2UKGgGR0AgAAAAAAAAaAdLCGgIR0A27nVG0/nodX2UKGgGR0AgAAAAAAAAaAdLCGgIR0A28I2OyVv/dX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A28qwyIpH7dX2UKGgGR0AmAAAAAAAAaAdLC2gIR0A29cIZ62ORdX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A2+NR3u/lAdX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A2+83Mpw0gdX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A2/kvsZ5zHdX2UKGgGR0AgAAAAAAAAaAdLCGgIR0A3AFtsN2C/dX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A3A8Gs3hn8dX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A3B0mtyPuHdX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A3Cd5IH1OCdX2UKGgGR0AmAAAAAAAAaAdLC2gIR0A3DNXYDklvdX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A3EAPuogmrdX2UKGgGR0AmAAAAAAAAaAdLC2gIR0A3EyVfNRm9dX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A3Fj7ALy+YdX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A3GYlY2bXpdX2UKGgGR0AgAAAAAAAAaAdLCGgIR0A3HCzkZJkHdX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A3Hps41gpjdX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A3Il05lvqDdX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A3JThYNiH7dX2UKGgGR0AkAAAAAAAAaAdLCmgIR0A3KLg4wRGudX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A3Kwb2lEZ0dX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A3LkC3gDRudX2UKGgGR0AmAAAAAAAAaAdLC2gIR0A3MSro4dZJdX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A3M4TsY2sJdX2UKGgGR0AiAAAAAAAAaAdLCWgIR0A3NjX4CZF5dWUu"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",

a2c_Cart_Pole/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25f7b53a93f615970eb450a258d9a10d7ba92d135dfdf68b30f709767417eba1
+oid sha256:7713c29cf916486d81ccdb13550753e2fac53454368add046a7c67d9dc2b68e7
 size 39937

a2c_Cart_Pole/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea35a559ee484d8eac5a95886de466628fce1c235586e65bab5034620ed73c0b
+oid sha256:e308b055b4ef028208227d49e71ccf5b6aa9bd67d0084533b3ffaa50d9f70ca3
 size 40705

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ", "__init__": "<function ActorCriticPolicy.__init__ at 0x00000234F67A4310>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x00000234F67A43A0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x00000234F67A4430>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x00000234F67A44C0>", "_build": "<function ActorCriticPolicy._build at 0x00000234F67A4550>", "forward": "<function ActorCriticPolicy.forward at 0x00000234F67A45E0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x00000234F67A4670>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x00000234F67A4700>", "_predict": "<function ActorCriticPolicy._predict at 0x00000234F67A4790>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x00000234F67A4820>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x00000234F67A48B0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x00000234F67A4940>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x00000234F67A0FC0>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [4], "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "bounded_below": "[ True  True  True  True]", "bounded_above": "[ True  True  True  True]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLAowGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 2, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "num_timesteps": 25000, "_total_timesteps": 25000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1676199912094791500, "learning_rate": 0.0007, "tensorboard_log": "runs/dcbpn4e8", "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAIPyQD4PnwW/LEcWvvQt+LyUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWV9QsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQDkAAAAAAACMAWyUSxmMAXSUR0AZDUSZjQRgdX2UKGgGR0BGAAAAAAAAaAdLLGgIR0AZNHe7+T/ydX2UKGgGR0BJgAAAAAAAaAdLM2gIR0AZXokiUxEfdX2UKGgGR0A4AAAAAAAAaAdLGGgIR0AZdQYUFjd6dX2UKGgGR0BLgAAAAAAAaAdLN2gIR0AZp5OafBepdX2UKGgGR0BFAAAAAAAAaAdLKmgIR0AZ3VMEidJ8dX2UKGgGR0BSAAAAAAAAaAdLSGgIR0AaHdWQwK0EdX2UKGgGR0BeQAAAAAAAaAdLeWgIR0AajJDE3sHCdX2UKGgGR0BJAAAAAAAAaAdLMmgIR0AatVIZqEeydX2UKGgGR0BcQAAAAAAAaAdLcWgIR0AbDfKp1ie/dX2UKGgGR0BgAAAAAAAAaAdLgGgIR0Abek56t1ZDdX2UKGgGR0BQwAAAAAAAaAdLQ2gIR0AbykzoEB8ydX2UKGgGR0BSgAAAAAAAaAdLSmgIR0AcCsT37DVIdX2UKGgGR0BBgAAAAAAAaAdLI2gIR0AcJv60pmVadX2UKGgGR0BVQAAAAAAAaAdLVWgIR0AccEfT1CgLdX2UKGgGR0BPAAAAAAAAaAdLPmgIR0AcoVzp5eJIdX2UKGgGR0BKAAAAAAAAaAdLNGgIR0Acyukk8ifQdX2UKGgGR0BfAAAAAAAAaAdLfGgIR0AdNDCxeLNwdX2UKGgGR0BQwAAAAAAAaAdLQ2gIR0AdhUMoc7yQdX2UKGgGR0BHAAAAAAAAaAdLLmgIR0Adr4Kx9oexdX2UKGgGR0BIgAAAAAAAaAdLMWgIR0Ad2OwPiDNAdX2UKGgGR0Bh4AAAAAAAaAdLj2gIR0AeTVtoBaLXdX2UKGgGR0A+AAAAAAAAaAdLHmgIR0AeZOLzf779dX2UKGgGR0BEgAAAAAAAaAdLKWgIR0AehNO/L1VYdX2UKGgGR0BTwAAAAAAAaAdLT2gIR0Aew4WDYh+wdX2UKGgGR0BTgAAAAAAAaAdLTmgIR0AfHEDQqqffdX2UKGgGR0BTgAAAAAAAaAdLTmgIR0AfXxUedTYNdX2UKGgGR0BLgAAAAAAAaAdLN2gIR0AfjGMn7YTTdX2UKGgGR0BGgAAAAAAAaAdLLWgIR0AfsBFNL128dX2UKGgGR0BYQAAAAAAAaAdLYWgIR0Af/UgB91EFdX2UKGgGR0BTwAAAAAAAaAdLT2gIR0AgIW3z+WGAdX2UKGgGR0BfgAAAAAAAaAdLfmgIR0AgVfsNUfgadX2UKGgGR0BYgAAAAAAAaAdLYmgIR0AgiHqNZNfxdX2UKGgGR0BDAAAAAAAAaAdLJmgIR0Agl7BO58SgdX2UKGgGR0BYgAAAAAAAaAdLYmgIR0Agvspobn5jdX2UKGgGR0BUQAAAAAAAaAdLUWgIR0Ag4RaHKwIMdX2UKGgGR0BYAAAAAAAAaAdLYGgIR0AhDSgGr0aqdX2UKGgGR0BjAAAAAAAAaAdLmGgIR0AhWJoCdSVGdX2UKGgGR0BZQAAAAAAAaAdLZWgIR0AhgfL9uP3jdX2UKGgGR0BRwAAAAAAAaAdLR2gIR0AhnnOjZcs2dX2UKGgGR0BMAAAAAAAAaAdLOGgIR0AhthYvFm4BdX2UKGgGR0BFgAAAAAAAaAdLK2gIR0Ahx6OYIBzWdX2UKGgGR0BhgAAAAAAAaAdLjGgIR0Ah/+b3Gn4xdX2UKGgGR0BUwAAAAAAAaAdLU2gIR0AiLsNUfgaWdX2UKGgGR0BgoAAAAAAAaAdLhWgIR0AiaudwvQF+dX2UKGgGR0BTQAAAAAAAaAdLTWgIR0AikUVSGahIdX2UKGgGR0BSwAAAAAAAaAdLS2gIR0AisQg9vCMxdX2UKGgGR0BRQAAAAAAAaAdLRWgIR0Aiy2w3YL9ddX2UKGgGR0BTwAAAAAAAaAdLT2gIR0Ai7XvH93r2dX2UKGgGR0BRwAAAAAAAaAdLR2gIR0AjF49ovi97dX2UKGgGR0BWQAAAAAAAaAdLWWgIR0AjPvqkdmxudX2UKGgGR0BZgAAAAAAAaAdLZmgIR0AjaQYDTz/ZdX2UKGgGR0BPgAAAAAAAaAdLP2gIR0Ajgx33YcvNdX2UKGgGR0BegAAAAAAAaAdLemgIR0AjtH0btJFtdX2UKGgGR0BegAAAAAAAaAdLemgIR0Aj9h3JPqLTdX2UKGgGR0BzkAAAAAAAaAdNOQFoCEdAJHvStvGZNXV9lChoBkdAaeAAAAAAAGgHS89oCEdAJN5H3Dej23V9lChoBkdAacAAAAAAAGgHS85oCEdAJTfmDDjzZ3V9lChoBkdAYgAAAAAAAGgHS5BoCEdAJXEv0yxiX3V9lChoBkdAW4AAAAAAAGgHS25oCEdAJasCLdepoHV9lChoBkdAZKAAAAAAAGgHS6VoCEdAJfBtUGVzIXV9lChoBkdAZCAAAAAAAGgHS6FoCEdAJjSVfNRm9XV9lChoBkdAdGAAAAAAAGgHTUYBaAhHQCbBnvlU6xR1fZQoaAZHQGhAAAAAAABoB0vCaAhHQCcZAlfJFLF1fZQoaAZHQGfgAAAAAABoB0u/aAhHQCd0DW9US7J1fZQoaAZHQGZgAAAAAABoB0uzaAhHQCe+IKtxMnJ1fZQoaAZHQHkwAAAAAABoB02TAWgIR0AoaxCY1He8dX2UKGgGR0BpAAAAAAAAaAdLyGgIR0AowDaoMrmRdX2UKGgGR0BsoAAAAAAAaAdL5WgIR0ApJrEcbR4RdX2UKGgGR0BrIAAAAAAAaAdL2WgIR0Apg5vtMPBjdX2UKGgGR0BpgAAAAAAAaAdLzGgIR0Ap5wVj7Q9idX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAKtIn0Cih4HV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQCu9nEl3Qld1fZQoaAZHQH9AAAAAAABoB030AWgIR0Asy4J/oaDPdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdALbN4A0bcXXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQC6Uzl90A951fZQoaAZHQHzwAAAAAABoB03PAWgIR0AvZckdFOO9dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAMCaSs8xKx3V9lChoBkdAdpAAAAAAAGgHTWkBaAhHQDB0/LTx5LR1fZQoaAZHQH9AAAAAAABoB030AWgIR0Aw68/2TPjXdX2UKGgGR0B0MAAAAAAAaAdNQwFoCEdAMT0uUUwi7nV9lChoBkdAfkAAAAAAAGgHTeQBaAhHQDG8q3EyckN1fZQoaAZHQHVgAAAAAABoB01WAWgIR0AyEhmGucMFdX2UKGgGR0BrIAAAAAAAaAdL2WgIR0AyTAHE/B3zdX2UKGgGR0BtwAAAAAAAaAdL7mgIR0AygvLX+VC5dX2UKGgGR0BgwAAAAAAAaAdLhmgIR0AypLfk3juKdX2UKGgGR0BigAAAAAAAaAdLlGgIR0AyxUmUnogWdX2UKGgGR0BkYAAAAAAAaAdLo2gIR0Ay6ZjQRf4RdX2UKGgGR0BhwAAAAAAAaAdLjmgIR0AzDhP0qYqodX2UKGgGR0BkoAAAAAAAaAdLpWgIR0AzMqJMxoIwdX2UKGgGR0B58AAAAAAAaAdNnwFoCEdAM5Gf029+PXV9lChoBkdAboAAAAAAAGgHS/RoCEdAM9E6T4cm0HV9lChoBkdAbEAAAAAAAGgHS+JoCEdANBBB7eEZi3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQDSRJPIn0Cl1fZQoaAZHQH9AAAAAAABoB030AWgIR0A1Cz9S/CZXdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdANYB0uDjBEnV9lChoBkdAc8AAAAAAAGgHTTwBaAhHQDXCDyvs7dV1fZQoaAZHQGkgAAAAAABoB0vJaAhHQDXuyB06o2p1fZQoaAZHQGRgAAAAAABoB0ujaAhHQDYQXZXdTHd1fZQoaAZHQH2wAAAAAABoB03bAWgIR0A2dq20AtFsdWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 5000, "n_steps": 5, "gamma": 0.99, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "normalize_advantage": false, "system_info": {"OS": "Windows-10-10.0.22621-SP0 10.0.22621", "Python": "3.10.2", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.0+cpu", "GPU Enabled": "False", "Numpy": "1.24.2", "Gym": "0.21.0"}}
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ", "__init__": "<function ActorCriticPolicy.__init__ at 0x000002925CA78AF0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x000002925CA78B80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x000002925CA78C10>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x000002925CA78CA0>", "_build": "<function ActorCriticPolicy._build at 0x000002925CA78D30>", "forward": "<function ActorCriticPolicy.forward at 0x000002925CA78DC0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x000002925CA78E50>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x000002925CA78EE0>", "_predict": "<function ActorCriticPolicy._predict at 0x000002925CA78F70>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x000002925CA79000>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x000002925CA79090>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x000002925CA79120>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x000002925CA71D40>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [4], "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "bounded_below": "[ True  True  True  True]", "bounded_above": "[ True  True  True  True]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLAowGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 2, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "num_timesteps": 25000, "_total_timesteps": 25000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1676202537295446500, "learning_rate": 0.0007, "tensorboard_log": "runs/mcfwzfhs", "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVnAIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMamM6XHVzZXJzXG1hdGhpXGFwcGRhdGFcbG9jYWxccHJvZ3JhbXNccHl0aG9uXHB5dGhvbjMxMFxsaWJcc2l0ZS1wYWNrYWdlc1xzdGFibGVfYmFzZWxpbmVzM1xjb21tb25cdXRpbHMucHmUjARmdW5jlEuCQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UaAx1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgefZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/RvAGjbi6x4WUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAP/fnL1hcm+/aH4LPYzjtD+UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 5000, "n_steps": 5, "gamma": 0.99, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "normalize_advantage": false, "system_info": {"OS": "Windows-10-10.0.22621-SP0 10.0.22621", "Python": "3.10.2", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.0+cpu", "GPU Enabled": "False", "Numpy": "1.24.2", "Gym": "0.21.0"}}

results.json

@@ -1 +1 @@
-{"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-12T12:05:47.887609"}
+{"mean_reward": 9.8, "std_reward": 0.6, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-12T12:49:33.386443"}