commit a2c-AntBulletEnv-v0

README.md

@@ -16,7 +16,7 @@ model-index:
       type: AntBulletEnv-v0
     metrics:
     - type: mean_reward
-      value: 2.77 +/- 2.60
+      value: 626.41 +/- 151.93
       name: mean_reward
       verified: false
 ---

a2c-AntBulletEnv-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f31900a8e740879df6ee6691b1622034b608c17ba283338cf88478deb36fe3b4
-size 125348
+oid sha256:53b11046eb65f3db56c9180926bef9df53c987a3f4925e19b80e5a459ac9fbaf
+size 129448

a2c-AntBulletEnv-v0/data

@@ -4,20 +4,20 @@
         ":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 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 0x749e8ceaf830>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x749e8ceaf8c0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x749e8ceaf950>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x749e8ceaf9e0>",
-        "_build": "<function ActorCriticPolicy._build at 0x749e8ceafa70>",
-        "forward": "<function ActorCriticPolicy.forward at 0x749e8ceafb00>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x749e8ceafb90>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x749e8ceafc20>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x749e8ceafcb0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x749e8ceafd40>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x749e8ceafdd0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x749e8ceafe60>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x757b2a0f7d40>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x757b2a0f7dd0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x757b2a0f7e60>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x757b2a0f7ef0>",
+        "_build": "<function ActorCriticPolicy._build at 0x757b2a0f7f80>",
+        "forward": "<function ActorCriticPolicy.forward at 0x757b2a0fd050>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x757b2a0fd0e0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x757b2a0fd170>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x757b2a0fd200>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x757b2a0fd290>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x757b2a0fd320>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x757b2a0fd3b0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x749e8cfbe600>"
+        "_abc_impl": "<_abc_data object at 0x757b2a0c07e0>"
     },
     "verbose": 1,
     "policy_kwargs": {
@@ -59,12 +59,12 @@
         "_np_random": null
     },
     "n_envs": 4,
-    "num_timesteps": 1024,
-    "_total_timesteps": 1000,
+    "num_timesteps": 5000000,
+    "_total_timesteps": 5000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1680811911147510681,
+    "start_time": 1680812267624404841,
     "learning_rate": 0.00096,
     "tensorboard_log": null,
     "lr_schedule": {
@@ -73,7 +73,7 @@
     },
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -81,21 +81,21 @@
     },
     "_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:": "gASV+gAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQCCSvA44p+eMAWyUSxqMAXSUR0BBFhBzFMqSdX2UKGgGR0Ac0mF8G9pRaAdLHGgIR0BBM1baAWi2dX2UKGgGR0Af3J7sv7FbaAdLFmgIR0BBSsGorFwUdX2UKGgGR0ANcD0UXYUWaAdLFWgIR0BBYBAnlXA/dX2UKGgGR0BIdF2mpEQYaAdLZWgIR0BBY9HMEA5rdX2UKGgGR0AS2CyyD7IlaAdLFmgIR0BBeZ5Rjz7NdX2UKGgGR0A6ZDmKZUkwaAdLWmgIR0BBumzru6VddWUu"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 32,
+    "_n_updates": 156250,
     "n_steps": 8,
     "gamma": 0.99,
     "gae_lambda": 0.9,

a2c-AntBulletEnv-v0/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb65b023b82abebdba57092abcc36d94de0ac8df2ce21683b6a4407923c7b238
-size 56062
+oid sha256:80fe4431eafdd9809d40ddc0f098e7c7d498eabd56e48876778d3035a1b4965c
+size 56190

a2c-AntBulletEnv-v0/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:051f894dd18ed7aceb81ec8f2385739349c32f3bcf7f2d0fca8ac3cd0a424f9e
-size 56830
+oid sha256:88509d6c1d265ecfc009c82c3aa5566e975f7a0852b181e99a1ee8dc02a550e2
+size 56958

a2c-AntBulletEnv-v0/system_info.txt

@@ -1,7 +1,7 @@
 - OS: Linux-5.15.90+-x86_64-with-debian-bullseye-sid # 1 SMP Sat Mar 25 11:28:03 UTC 2023
 - Python: 3.7.12
 - Stable-Baselines3: 1.7.0
-- PyTorch: 1.13.0+cpu
-- GPU Enabled: False
+- PyTorch: 1.13.0
+- 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 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 0x749e8ceaf830>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x749e8ceaf8c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x749e8ceaf950>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x749e8ceaf9e0>", "_build": "<function ActorCriticPolicy._build at 0x749e8ceafa70>", "forward": "<function ActorCriticPolicy.forward at 0x749e8ceafb00>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x749e8ceafb90>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x749e8ceafc20>", "_predict": "<function ActorCriticPolicy._predict at 0x749e8ceafcb0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x749e8ceafd40>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x749e8ceafdd0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x749e8ceafe60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x749e8cfbe600>"}, "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": 1680811911147510681, "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:": "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:": "gASV+gAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQCCSvA44p+eMAWyUSxqMAXSUR0BBFhBzFMqSdX2UKGgGR0Ac0mF8G9pRaAdLHGgIR0BBM1baAWi2dX2UKGgGR0Af3J7sv7FbaAdLFmgIR0BBSsGorFwUdX2UKGgGR0ANcD0UXYUWaAdLFWgIR0BBYBAnlXA/dX2UKGgGR0BIdF2mpEQYaAdLZWgIR0BBY9HMEA5rdX2UKGgGR0AS2CyyD7IlaAdLFmgIR0BBeZ5Rjz7NdX2UKGgGR0A6ZDmKZUkwaAdLWmgIR0BBumzru6VddWUu"}, "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-5.15.90+-x86_64-with-debian-bullseye-sid # 1 SMP Sat Mar 25 11:28:03 UTC 2023", "Python": "3.7.12", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.0+cpu", "GPU Enabled": "False", "Numpy": "1.21.6", "Gym": "0.21.0"}}
+{"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 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 0x757b2a0f7d40>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x757b2a0f7dd0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x757b2a0f7e60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x757b2a0f7ef0>", "_build": "<function ActorCriticPolicy._build at 0x757b2a0f7f80>", "forward": "<function ActorCriticPolicy.forward at 0x757b2a0fd050>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x757b2a0fd0e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x757b2a0fd170>", "_predict": "<function ActorCriticPolicy._predict at 0x757b2a0fd200>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x757b2a0fd290>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x757b2a0fd320>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x757b2a0fd3b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x757b2a0c07e0>"}, "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": 5000000, "_total_timesteps": 5000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1680812267624404841, "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:": "gASVjAAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwSFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDBAAAAACUdJRiLg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gASVTQIAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwRLHIaUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiULAAQAAAAAAAOq0izYAAIA/AAAAAAAAAAAAAAAAAAAAAAAAAIAVXDA5AAAAACFp6b8AAAAAA/HbPQAAAADHsv8/AAAAAJ//7z0AAAAAxbPfPwAAAADGFi49AAAAAN4AAcAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA9oMO2AACAPwAAAAAAAAAAAAAAAAAAAAAAAACApRiLPQAAAADR5Py/AAAAAIZe0j0AAAAAibDhPwAAAACNbwy+AAAAALfH/j8AAAAAockPPgAAAABZ5Pi/AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAANAo3NQAAgD8AAAAAAAAAAAAAAAAAAAAAAAAAgGCq7D0AAAAAmhXfvwAAAACPlRc9AAAAADCg3T8AAAAAaubavAAAAABlXds/AAAAAMO9C74AAAAATFXgvwAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAOpZ/zYAAIA/AAAAAAAAAAAAAAAAAAAAAAAAAIDaPYk8AAAAAEtvAMAAAAAAxZK2PQAAAACCpvc/AAAAAGKdDj4AAAAA8mMAQAAAAAD4sAG+AAAAAF7w/78AAAAAAAAAAAAAAAAAAAAAAAAAAJR0lGIu"}, "_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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 156250, "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-5.15.90+-x86_64-with-debian-bullseye-sid # 1 SMP Sat Mar 25 11:28:03 UTC 2023", "Python": "3.7.12", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.0", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.21.0"}}

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9647cf8df079fa971a06cfcc25381559617edc2d9039c4b504e678921efd64a2
-size 1428666
+oid sha256:f89c8e6a3685309395146dbf2ef83b691cadca83e52d0773a4da18705f1a29b4
+size 305208

results.json

@@ -1 +1 @@
-{"mean_reward": 2.769964184281707, "std_reward": 2.603468948775433, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-06T20:12:55.415895"}
+{"mean_reward": 626.4061678627583, "std_reward": 151.92508237195705, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-06T22:32:16.457277"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f082adee3c210efa5667cd6e03f2cd6393cdb1a4850184dbf1855d49b93ec3ca
+oid sha256:5cb6f448fe99935a7eac21f62c4c6168668c1ea0a8704199f324fe4696976cb1
 size 2371