Initial commit

README.md

@@ -8,16 +8,17 @@ tags:
 model-index:
 - name: A2C
   results:
-  - metrics:
-    - type: mean_reward
-      value: 434.14 +/- 66.87
-      name: mean_reward
-    task:
+  - task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
       name: AntBulletEnv-v0
       type: AntBulletEnv-v0
+    metrics:
+    - type: mean_reward
+      value: 420.96 +/- 142.32
+      name: mean_reward
+      verified: false
 ---
 
 # **A2C** Agent playing **AntBulletEnv-v0**

a2c-AntBulletEnv-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5538ec0e7021009d23166b0df931bab24eebda16739113b392c80f0883e6ba1
-size 125261
+oid sha256:af238283c249a5a406ab4d215db8553837492ee142d9c146d7a998013a3b05ad
+size 125571

a2c-AntBulletEnv-v0/_stable_baselines3_version

@@ -1 +1 @@
-1.6.0
+1.7.0

a2c-AntBulletEnv-v0/data

@@ -1,27 +1,28 @@
 {
     "policy_class": {
         ":type:": "<class 'abc.ABCMeta'>",
-        ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
+        ":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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7f6454f2def0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6454f2df80>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6454f31050>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6454f310e0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f6454f31170>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f6454f31200>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6454f31290>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f6454f31320>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6454f313b0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6454f31440>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6454f314d0>",
+        "__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 0x7fe013656ee0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fe013656f70>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fe01365e040>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fe01365e0d0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fe01365e160>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fe01365e1f0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fe01365e280>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fe01365e310>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fe01365e3a0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fe01365e430>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fe01365e4c0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fe01365e550>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7f6454f81780>"
+        "_abc_impl": "<_abc_data object at 0x7fe01364acc0>"
     },
     "verbose": 1,
     "policy_kwargs": {
         ":type:": "<class 'dict'>",
-        ":serialized:": "gASVowAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/v///4wKb3J0aG9faW5pdJSJjA9vcHRpbWl6ZXJfY2xhc3OUjBN0b3JjaC5vcHRpbS5ybXNwcm9wlIwHUk1TcHJvcJSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lCiMBWFscGhhlEc/764UeuFHrowDZXBzlEc+5Pi1iONo8YwMd2VpZ2h0X2RlY2F5lEsAdXUu",
+        ":serialized:": "gAWVowAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/v///4wKb3J0aG9faW5pdJSJjA9vcHRpbWl6ZXJfY2xhc3OUjBN0b3JjaC5vcHRpbS5ybXNwcm9wlIwHUk1TcHJvcJSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lCiMBWFscGhhlEc/764UeuFHrowDZXBzlEc+5Pi1iONo8YwMd2VpZ2h0X2RlY2F5lEsAdXUu",
         "log_std_init": -2,
         "ortho_init": false,
         "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>",
@@ -33,7 +34,7 @@
     },
     "observation_space": {
         ":type:": "<class 'gym.spaces.box.Box'>",
-        ":serialized:": "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",
+        ":serialized:": "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",
         "dtype": "float32",
         "_shape": [
             28
@@ -46,7 +47,7 @@
     },
     "action_space": {
         ":type:": "<class 'gym.spaces.box.Box'>",
-        ":serialized:": "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",
+        ":serialized:": "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",
         "dtype": "float32",
         "_shape": [
             8
@@ -58,44 +59,44 @@
         "_np_random": null
     },
     "n_envs": 4,
-    "num_timesteps": 1024,
-    "_total_timesteps": 1000,
+    "num_timesteps": 10000,
+    "_total_timesteps": 10000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1658738092.0043716,
+    "start_time": 1673942858453034411,
     "learning_rate": 0.00096,
-    "tensorboard_log": "./tensorboard",
+    "tensorboard_log": null,
     "lr_schedule": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gASVjAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwSFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDBAAAAACUdJRiLg=="
+        ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
     },
     "_last_original_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "_episode_num": 0,
     "use_sde": true,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.02400000000000002,
+    "_current_progress_remaining": 0.0,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gASVvgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQBrCYkVvddqMAWyUSxSMAXSUR0B7RiC04R29dX2UKGgGR0AYbvb48EFGaAdLFGgIR0B7RiJtSAH3dX2UKGgGR0AykfigkC3gaAdLOGgIR0B7SaraM72ddX2UKGgGR0BUTIoZydWiaAdLiWgIR0B7U46Lfk3kdX2UKGgGR0BRBqiCaqjraAdLuWgIR0B7VkmReTmodWUu"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 32,
-    "n_steps": 8,
+    "_n_updates": 2500,
+    "n_steps": 1,
     "gamma": 0.99,
     "gae_lambda": 0.9,
     "ent_coef": 0.0,

a2c-AntBulletEnv-v0/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a01f6e19c96e995a9bf2306a0fb51b1085f35a2e59a2d35dbec1291f13a4bfc6
-size 56126
+oid sha256:4aca11769ea026e59c7bd613384e5dfbc9322a9efbc9c084b71cf021b7717bce
+size 56190

a2c-AntBulletEnv-v0/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8462bcb302d11f1207b3b430c65f8e51b1370f255754ff1bbdc0ae1d1a4f33dd
-size 56766
+oid sha256:06eb8817a06a0af0757127e0bd565cad3f5bd7456850626f4e3d1d73c6f693c3
+size 56958

a2c-AntBulletEnv-v0/system_info.txt

@@ -1,7 +1,7 @@
-OS: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
-Python: 3.7.13
-Stable-Baselines3: 1.6.0
-PyTorch: 1.12.0+cu113
-GPU Enabled: True
-Numpy: 1.21.6
-Gym: 0.21.0
+- OS: Linux-5.10.147+-x86_64-with-glibc2.27 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
+- Python: 3.8.16
+- Stable-Baselines3: 1.7.0
+- PyTorch: 1.13.0+cu116
+- GPU Enabled: True
+- Numpy: 1.21.6
+- Gym: 0.21.0

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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 sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\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 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 0x7f6454f2def0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6454f2df80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6454f31050>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6454f310e0>", "_build": "<function ActorCriticPolicy._build at 0x7f6454f31170>", "forward": "<function ActorCriticPolicy.forward at 0x7f6454f31200>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6454f31290>", "_predict": "<function ActorCriticPolicy._predict at 0x7f6454f31320>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6454f313b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6454f31440>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6454f314d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f6454f81780>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gASVowAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/v///4wKb3J0aG9faW5pdJSJjA9vcHRpbWl6ZXJfY2xhc3OUjBN0b3JjaC5vcHRpbS5ybXNwcm9wlIwHUk1TcHJvcJSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lCiMBWFscGhhlEc/764UeuFHrowDZXBzlEc+5Pi1iONo8YwMd2VpZ2h0X2RlY2F5lEsAdXUu", "log_std_init": -2, "ortho_init": false, "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": [28], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]", "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]", "high": "[1. 1. 1. 1. 1. 1. 1. 1.]", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_np_random": null}, "n_envs": 4, "num_timesteps": 1024, "_total_timesteps": 1000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1658738092.0043716, "learning_rate": 0.00096, "tensorboard_log": "./tensorboard", "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gASVjAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwSFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDBAAAAACUdJRiLg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_episode_num": 0, "use_sde": true, "sde_sample_freq": -1, "_current_progress_remaining": -0.02400000000000002, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVvgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQBrCYkVvddqMAWyUSxSMAXSUR0B7RiC04R29dX2UKGgGR0AYbvb48EFGaAdLFGgIR0B7RiJtSAH3dX2UKGgGR0AykfigkC3gaAdLOGgIR0B7SaraM72ddX2UKGgGR0BUTIoZydWiaAdLiWgIR0B7U46Lfk3kdX2UKGgGR0BRBqiCaqjraAdLuWgIR0B7VkmReTmodWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 32, "n_steps": 8, "gamma": 0.99, "gae_lambda": 0.9, "ent_coef": 0.0, "vf_coef": 0.4, "max_grad_norm": 0.5, "normalize_advantage": false, "system_info": {"OS": "Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022", "Python": "3.7.13", "Stable-Baselines3": "1.6.0", "PyTorch": "1.12.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "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 0x7fe013656ee0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fe013656f70>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fe01365e040>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fe01365e0d0>", "_build": "<function ActorCriticPolicy._build at 0x7fe01365e160>", "forward": "<function ActorCriticPolicy.forward at 0x7fe01365e1f0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fe01365e280>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fe01365e310>", "_predict": "<function ActorCriticPolicy._predict at 0x7fe01365e3a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fe01365e430>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fe01365e4c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fe01365e550>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fe01364acc0>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVowAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/v///4wKb3J0aG9faW5pdJSJjA9vcHRpbWl6ZXJfY2xhc3OUjBN0b3JjaC5vcHRpbS5ybXNwcm9wlIwHUk1TcHJvcJSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lCiMBWFscGhhlEc/764UeuFHrowDZXBzlEc+5Pi1iONo8YwMd2VpZ2h0X2RlY2F5lEsAdXUu", "log_std_init": -2, "ortho_init": false, "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": [28], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]", "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]", "high": "[1. 1. 1. 1. 1. 1. 1. 1.]", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_np_random": null}, "n_envs": 4, "num_timesteps": 10000, "_total_timesteps": 10000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1673942858453034411, "learning_rate": 0.00096, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_episode_num": 0, "use_sde": true, "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": 2500, "n_steps": 1, "gamma": 0.99, "gae_lambda": 0.9, "ent_coef": 0.0, "vf_coef": 0.4, "max_grad_norm": 0.5, "normalize_advantage": false, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.27 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.16", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.0+cu116", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}

results.json

@@ -1 +1 @@
-{"mean_reward": 434.13707664154936, "std_reward": 66.87121672129756, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-07-25T08:37:53.424223"}
+{"mean_reward": 420.9580152107501, "std_reward": 142.31554186212912, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-17T08:09:21.048686"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef5ffa03565f2440db5583ad54387900ce5f91ec5f4259cf2b8afea106b64f10
-size 2763
+oid sha256:15711f5a2abbc3c230aa36d6293aed2d571a8d79f26a45e6f801e99cab82d27d
+size 2521