train with different seed

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 1498.70 +/- 811.27
+      value: 1597.89 +/- 61.16
       name: mean_reward
     task:
       type: reinforcement-learning

a2c-HalfCheetahBulletEnv-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b3cf6e1bee8759d3aa5ce12e03a9310d673d2f34074d3ae0eefc47e0d300ab
-size 121752
+oid sha256:37760f5e3f09fb4d248c26925eb3524403e7cd05e022754f8d372b654895f84c
+size 124729

a2c-HalfCheetahBulletEnv-v0/data

@@ -4,19 +4,19 @@
         ":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 0x7f29c7aff3a0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f29c7aff430>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f29c7aff4c0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f29c7aff550>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f29c7aff5e0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f29c7aff670>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f29c7aff700>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f29c7aff790>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f29c7aff820>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f29c7aff8b0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f29c7aff940>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fe60dc823a0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fe60dc82430>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fe60dc824c0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fe60dc82550>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fe60dc825e0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fe60dc82670>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fe60dc82700>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fe60dc82790>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fe60dc82820>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fe60dc828b0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fe60dc82940>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f29c7cc8e00>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fe60dc88f40>"
     },
     "verbose": 1,
     "policy_kwargs": {
@@ -57,13 +57,13 @@
         "bounded_above": "[ True  True  True  True  True  True]",
         "_np_random": null
     },
-    "n_envs": 8,
-    "num_timesteps": 0,
+    "n_envs": 4,
+    "num_timesteps": 2000000,
     "_total_timesteps": 2000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1659352750.6474247,
+    "start_time": 1659352981.0213437,
     "learning_rate": 0.00096,
     "tensorboard_log": "./tensorboard",
     "lr_schedule": {
@@ -72,15 +72,15 @@
     },
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVewAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAAEBAQEBAQEBlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlC4="
+        ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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,
@@ -88,13 +88,13 @@
     "_current_progress_remaining": 0.0,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 156250,
+    "_n_updates": 62500,
     "n_steps": 8,
     "gamma": 0.99,
     "gae_lambda": 0.9,

a2c-HalfCheetahBulletEnv-v0/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:881db562d557671f8ffab3f407b366985fab53b319ab8a86670c9fe51101be5e
-size 54142
+oid sha256:66fb8efb43c8569db1a0c28b5b27f6822a7f36435f3e4880edd6c25a5ef7ecb2
+size 54078

a2c-HalfCheetahBulletEnv-v0/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81a732e964155b759d816eb58cf0534ed628c9f523ddcf17c76c11aa24012bb1
+oid sha256:baea0b47859de337c9ea35ca475a7032328d5d8803d72925219af38f14c20787
 size 54718

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 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 0x7f29c7aff3a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f29c7aff430>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f29c7aff4c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f29c7aff550>", "_build": "<function ActorCriticPolicy._build at 0x7f29c7aff5e0>", "forward": "<function ActorCriticPolicy.forward at 0x7f29c7aff670>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f29c7aff700>", "_predict": "<function ActorCriticPolicy._predict at 0x7f29c7aff790>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f29c7aff820>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f29c7aff8b0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f29c7aff940>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f29c7cc8e00>"}, "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": [26], "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]", "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]", "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]", "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]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [6], "low": "[-1. -1. -1. -1. -1. -1.]", "high": "[1. 1. 1. 1. 1. 1.]", "bounded_below": "[ True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True]", "_np_random": null}, "n_envs": 8, "num_timesteps": 0, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1659352750.6474247, "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:": "gAWVewAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYIAAAAAAAAAAEBAQEBAQEBlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlC4="}, "_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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_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-5.11.0-38-generic-x86_64-with-glibc2.31 #42~20.04.1-Ubuntu SMP Tue Sep 28 20:41:07 UTC 2021", "Python": "3.9.12", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu102", "GPU Enabled": "True", "Numpy": "1.22.3", "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 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 0x7fe60dc823a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fe60dc82430>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fe60dc824c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fe60dc82550>", "_build": "<function ActorCriticPolicy._build at 0x7fe60dc825e0>", "forward": "<function ActorCriticPolicy.forward at 0x7fe60dc82670>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fe60dc82700>", "_predict": "<function ActorCriticPolicy._predict at 0x7fe60dc82790>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fe60dc82820>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fe60dc828b0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fe60dc82940>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fe60dc88f40>"}, "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": [26], "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]", "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]", "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]", "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]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [6], "low": "[-1. -1. -1. -1. -1. -1.]", "high": "[1. 1. 1. 1. 1. 1.]", "bounded_below": "[ True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True]", "_np_random": null}, "n_envs": 4, "num_timesteps": 2000000, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1659352981.0213437, "learning_rate": 0.00096, "tensorboard_log": "./tensorboard", "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWV9wIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwNX2J1aWx0aW5fdHlwZZSTlIwKTGFtYmRhVHlwZZSFlFKUKGgCjAhDb2RlVHlwZZSFlFKUKEsBSwBLAEsBSwFLE0MEiABTAJROhZQpjAFflIWUjGMvaG9tZS9ubS9hbmFjb25kYTMvZW52cy9kZWVwLXJsLWNsYXNzL2xpYi9weXRob24zLjkvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuAQwIAAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjGMvaG9tZS9ubS9hbmFjb25kYTMvZW52cy9kZWVwLXJsLWNsYXNzL2xpYi9weXRob24zLjkvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoIH2UfZQoaBdoDowMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBiMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP091EE1VHWmFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": 62500, "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-5.11.0-38-generic-x86_64-with-glibc2.31 #42~20.04.1-Ubuntu SMP Tue Sep 28 20:41:07 UTC 2021", "Python": "3.9.12", "Stable-Baselines3": "1.5.0", "PyTorch": "1.11.0+cu102", "GPU Enabled": "True", "Numpy": "1.22.3", "Gym": "0.21.0"}}

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2039d93a92960e1736026fd44316515c265b3a380dd66a279e3e3d3f578068e9
-size 1213533
+oid sha256:93a9e3f8743826696dd6d5d8327143fdd4a2155203b6f02d0b01858206f07cd9
+size 858064

results.json

@@ -1 +1 @@
-{"mean_reward": 1498.700125034753, "std_reward": 811.270000971616, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-08-01T13:19:53.773557"}
+{"mean_reward": 1597.888242291729, "std_reward": 61.1578555739329, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-08-01T14:17:41.667092"}