Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 54.69 +/- 142.83
+      value: 211.28 +/- 23.29
       name: mean_reward
       verified: false
 ---

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 0x793aa92a9b40>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x793aa92a9bd0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x793aa92a9c60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x793aa92a9cf0>", "_build": "<function ActorCriticPolicy._build at 0x793aa92a9d80>", "forward": "<function ActorCriticPolicy.forward at 0x793aa92a9e10>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x793aa92a9ea0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x793aa92a9f30>", "_predict": "<function ActorCriticPolicy._predict at 0x793aa92a9fc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x793aa92aa050>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x793aa92aa0e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x793aa92aa170>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x793aa924af80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 200704, "_total_timesteps": 200000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1708800273301428566, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAGYbbj4PIhk9wkTVuWk+KbjQyK0+hd6CuQAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_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": -0.0035199999999999676, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 980, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
+{"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 0x7dda85068310>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7dda850683a0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7dda85068430>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7dda850684c0>", "_build": "<function ActorCriticPolicy._build at 0x7dda85068550>", "forward": "<function ActorCriticPolicy.forward at 0x7dda850685e0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7dda85068670>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7dda85068700>", "_predict": "<function ActorCriticPolicy._predict at 0x7dda85068790>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7dda85068820>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7dda850688b0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7dda85068940>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7dda85015d80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 200704, "_total_timesteps": 200000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1709902201009110303, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAN49Bj/c0CA9XH2DvKe2djwggZ694vRKPQAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_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": -0.0035199999999999676, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 980, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVdgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

results.json

@@ -1 +1 @@
-{"mean_reward": 54.692337699999996, "std_reward": 142.83392620520007, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-24T19:08:52.437026"}
+{"mean_reward": 211.27658060000005, "std_reward": 23.28788491754017, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-08T12:58:57.675912"}

test.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c0c17327b5fca9b4cee95c26eeeae93a0ca7b4378cdb012ab7924182e12d9b1
-size 147421
+oid sha256:946c7d182716a5a724323f0259a8c8660dd01004ffe3e8f8a1a23137f88c537b
+size 147409

test/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 0x793aa92a9b40>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x793aa92a9bd0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x793aa92a9c60>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x793aa92a9cf0>",
-        "_build": "<function ActorCriticPolicy._build at 0x793aa92a9d80>",
-        "forward": "<function ActorCriticPolicy.forward at 0x793aa92a9e10>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x793aa92a9ea0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x793aa92a9f30>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x793aa92a9fc0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x793aa92aa050>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x793aa92aa0e0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x793aa92aa170>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7dda85068310>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7dda850683a0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7dda85068430>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7dda850684c0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7dda85068550>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7dda850685e0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7dda85068670>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7dda85068700>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7dda85068790>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7dda85068820>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7dda850688b0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7dda85068940>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x793aa924af80>"
+        "_abc_impl": "<_abc._abc_data object at 0x7dda85015d80>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -26,12 +26,12 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1708800273301428566,
+    "start_time": 1709902201009110303,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAGYbbj4PIhk9wkTVuWk+KbjQyK0+hd6CuQAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAN49Bj/c0CA9XH2DvKe2djwggZ694vRKPQAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -45,7 +45,7 @@
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "gAWVOAwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQGRzmlQ/HHaMAWyUTRcCjAF0lEdAdj0o4MnZ03V9lChoBkfANvepbUwztWgHTYMBaAhHQHZGAT7EYO51fZQoaAZHQGgWmrCFbmloB02nAWgIR0B2ZdkXk5p8dX2UKGgGR0BvGdOdoWYXaAdNhQFoCEdAdm8FxXGOuXV9lChoBkdAaIET37DVIGgHTb8BaAhHQHZ45fpljEx1fZQoaAZHwC+IVj7Q9idoB01gAWgIR0B2gNc0Ltu2dX2UKGgGR0BpunqRlpXZaAdN2wFoCEdAdotKjSG8EnV9lChoBkdAaKZPY4ACGWgHTaEBaAhHQHaq3PAwfyR1fZQoaAZHQGmm5BLPD51oB02NAWgIR0B2s716E8JVdX2UKGgGR0BpUofEGZ/kaAdNxQJoCEdAdsOs4T9KmXV9lChoBkdAZ2u7PIGQjmgHTaABaAhHQHbM5PhybQV1fZQoaAZHQG1k+wkgOjJoB02jAWgIR0B28ExmCiAUdX2UKGgGR0Bv6ebmU4aQaAdNggFoCEdAdvyBfa6BiHV9lChoBkdAa7k6e5Fw1mgHTRACaAhHQHcISD7Ikqt1fZQoaAZHQGpG2ZJCjUNoB02UAWgIR0B3EYVRDTjOdX2UKGgGR0BtTaWTot+TaAdNaAFoCEdAdxmPxhDw6XV9lChoBkdAaoTUdaMaTGgHTYUBaAhHQHc4nndO6/Z1fZQoaAZHwCBwx+KCQLhoB0v4aAhHQHc+LuQZGax1fZQoaAZHwB9DmnwXqJNoB00qAWgIR0B3RQ2eg+QmdX2UKGgGR0Bv/ImE4//vaAdNnwFoCEdAd05/HYHxBnV9lChoBkfAS54Z62OQyWgHTTABaAhHQHdVO1fE4vN1fZQoaAZHQGvKYZEUj9poB01eAWgIR0B3XNIClrM1dX2UKGgGR0BqJHPTodMkaAdNbwFoCEdAd3tZ2pyZKHV9lChoBkdAcAGOtGNJe2gHTXQBaAhHQHeD2IwdsBR1fZQoaAZHwFfBnnuAqd9oB01JAWgIR0B3i3NgSeyzdX2UKGgGR0BtKP8AJb+taAdNlAFoCEdAd5S9deIEbHV9lChoBkdAaqNtRekYXWgHTWEBaAhHQHec+6NEPUd1fZQoaAZHQG76fIS13MZoB01KAWgIR0B3pschkiD/dX2UKGgGR0Altu3MINVjaAdL5mgIR0B3x5FSbYsedX2UKGgGR0A51029+PRzaAdNQAFoCEdAd86oNd7fHnV9lChoBkdAbKgvtdAxBWgHTVYBaAhHQHfWW1MM7U51fZQoaAZHQHDb84DLbHpoB01eAWgIR0B33jRUm2LHdX2UKGgGR0BtSBiVjZtfaAdNcwFoCEdAd+cV/+bVjXV9lChoBkdAU1Ag7o0Q9WgHTegDaAhHQHgUkHyEtd11fZQoaAZHwEHcacZtNztoB00fAWgIR0B4G2cQRPGidX2UKGgGR0BuJCSidrftaAdNlQFoCEdAeCSE9t/FznV9lChoBkdAYEcCYkVvdmgHTegDaAhHQHhSUrsjVx11fZQoaAZHQGzx096kZaVoB01kAWgIR0B4Wrq6e5FxdX2UKGgGR0Bs2lNUOuq4aAdNVAFoCEdAeGT5TIeYD3V9lChoBkdAb4NbHp8neGgHTU4BaAhHQHhu+zyBkI51fZQoaAZHQDO/Mmnfl6toB005AWgIR0B4eVDIBBAwdX2UKGgGR0Bu/Z+F10T2aAdN4AFoCEdAeIVg3tKIznV9lChoBkfAQbFnscABDGgHTQgBaAhHQHihiXD3ueB1fZQoaAZHQENnp7kXDWNoB00vAWgIR0B4qEKRdQfqdX2UKGgGR0Btlxrvb48EaAdNNQFoCEdAeK+Eh7mdRXV9lChoBkdAbyfrYXfqHGgHTTsBaAhHQHi2mu5jH4p1fZQoaAZHwDX3GipNsWRoB00EAWgIR0B4vG9IwudxdX2UKGgGR0BwqRTgl4TsaAdNigFoCEdAeMUObAk9lnV9lChoBkdAbZFOxjawlmgHTVMBaAhHQHjjIHxBmf51fZQoaAZHQGN1UEgW8AdoB02xAWgIR0B47QqgAZKndX2UKGgGR0BtoraVUuL8aAdNagFoCEdAePWBT4tYjnV9lChoBkfABd5fMOf/WGgHTRkBaAhHQHj729US7Gx1fZQoaAZHQC3OSU1Q66toB00PAWgIR0B5AhTVDrqudX2UKGgGR8BFu9yDIzWPaAdNKgFoCEdAeQjXw9aEBnV9lChoBkdAaiKstkFwDWgHTVMBaAhHQHkQw++ueSV1fZQoaAZHwAsJWeYlY2doB00DAWgIR0B5MdztCzC2dX2UKGgGR8BNHvMSsbNsaAdNDQFoCEdAeTp8x9G7SXV9lChoBkdAbdEFXaJyhmgHTUQBaAhHQHlBmNFSbYt1fZQoaAZHQG83kLH+6y1oB01DAWgIR0B5SM46wMYudX2UKGgGR0BwY28scyWSaAdNgQFoCEdAeVFzfaYeDHV9lChoBkdAaqDjslb/wWgHTVgBaAhHQHlY/8Muvll1fZQoaAZHQDoEAXEZR9BoB0v1aAhHQHlzqvRqoIh1fZQoaAZHQHEZy/47A+JoB02aAWgIR0B5fLrPdEb6dX2UKGgGR8AlNWKdhAnlaAdLpmgIR0B5gIo7V8TjdX2UKGgGR0BmVKJsO5J9aAdNqwFoCEdAeYnI7vG6w3V9lChoBkdAJtS4vvjOs2gHS7hoCEdAeY4JrtVrAXV9lChoBkfAOPS+tbLU1GgHS/toCEdAeZPwAEMb33V9lChoBkdAa7+QiiZfD2gHTVcBaAhHQHmbapHZsbh1fZQoaAZHQCkI2dd3SrpoB0vbaAhHQHm18vh60IF1fZQoaAZHQHBxvGZNO/NoB01dAWgIR0B5vaSA6MisdX2UKGgGR0AeB9qk/KQraAdL5WgIR0B5wt/PPcBVdX2UKGgGR0A0t4tHxz7uaAdL22gIR0B5x7+NtIkJdX2UKGgGR0BwCbpX6qKhaAdNugFoCEdAedGvqC6H03V9lChoBkdAbQpcAzYVZmgHTYYBaAhHQHnaZ8a4tpV1fZQoaAZHQG+LAHmig01oB01EAWgIR0B55Ee9zwMIdX2UKGgGR0Bv1s9jgAIZaAdNYwFoCEdAegooMa0hNnV9lChoBkfACrzHS4OMEWgHS/JoCEdAehClmvnr6nV9lChoBkdAI3lf7aZhKGgHTRABaAhHQHoY6OktVaR1fZQoaAZHQG4KJ6hQFcJoB02LAWgIR0B6JD0wrUb2dX2UKGgGR0Bq7vCfpUxVaAdNcAFoCEdAeixbVBlcyHV9lChoBkfAHKXtBv73wmgHTQwBaAhHQHoyTYdyT6l1fZQoaAZHQG8iPHDJlrdoB01FAWgIR0B6T6/TLGJfdX2UKGgGR0BvgYL3K0UoaAdNZQFoCEdAeleH0se4kXV9lChoBkdAUGXxFy7wrmgHTegDaAhHQHpuSHuZ1FJ1fZQoaAZHQArz4L1EmY1oB00rAWgIR0B6dORfWtlqdX2UKGgGR0BsJetKZlWfaAdNcgFoCEdAepNbKifxt3V9lChoBkdAJY36ZYxL02gHS9doCEdAepgkiD/VAnV9lChoBkdAV8EmhM8HOmgHTegDaAhHQHq1CZOSGJx1fZQoaAZHQG4Svk7wKBxoB01uAWgIR0B6vk8EFGG3dX2UKGgGR0Brm+TA31jBaAdNVAFoCEdAesXXxOLzgHV9lChoBkdAcFdMRHww02gHTWYBaAhHQHrkGh7E5yV1fZQoaAZHQG3qnBtUGV1oB02LAWgIR0B67Nhpg1FZdX2UKGgGR0Bsz3rt3OfNaAdNfgFoCEdAevU1/2Cd0HV9lChoBkdAbuZstTUAk2gHTVsBaAhHQHr83XRPXTV1fZQoaAZHQFrRMgEEC/5oB03oA2gIR0B7KPN7jT8YdX2UKGgGR8BFaXYtg8bJaAdNGgFoCEdAey+NpM6BAnV9lChoBke//7OyE+Pik2gHS/poCEdAezUVKf4AS3V9lChoBkfAURCZH/cWTGgHTTIBaAhHQHs7u/gzguR1fZQoaAZHQB5FdC3PRiRoB00LAWgIR0B7QZ58jRlZdX2UKGgGR8BBHB5HEuQIaAdNQgFoCEdAe0iaKDTScHVlLg=="
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",

test/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b23d551aca4158037de2d63c86b99212954fb5f9c336adbd44aa01f54a9b674c
+oid sha256:e7e778a5eb4ee79d2768d3c5dc6b0ffe1cc800240dae4702e92ab61c4811d576
 size 88362

test/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09158639c439c87b3307d69ece7ebacd73372b7b6f602f298760ca1dc13bf94d
+oid sha256:bd5bcb73a3f9ba75cbda5b7a18d7b81cf9c7d5695f813e119e4aaf8f32c07c38
 size 43762