Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 228.54 +/- 62.97
+      value: 259.55 +/- 14.51
       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 0x7b2dd83c9630>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b2dd83c96c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b2dd83c9750>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b2dd83c97e0>", "_build": "<function ActorCriticPolicy._build at 0x7b2dd83c9870>", "forward": "<function ActorCriticPolicy.forward at 0x7b2dd83c9900>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b2dd83c9990>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b2dd83c9a20>", "_predict": "<function ActorCriticPolicy._predict at 0x7b2dd83c9ab0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b2dd83c9b40>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b2dd83c9bd0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b2dd83c9c60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7b2dd855e840>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1704127797584510600, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_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": 248, "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:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "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": "1.23.5", "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 0x7957f6c1fb50>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7957f6c1fbe0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7957f6c1fc70>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7957f6c1fd00>", "_build": "<function ActorCriticPolicy._build at 0x7957f6c1fd90>", "forward": "<function ActorCriticPolicy.forward at 0x7957f6c1fe20>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7957f6c1feb0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7957f6c1ff40>", "_predict": "<function ActorCriticPolicy._predict at 0x7957f6c24040>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7957f6c240d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7957f6c24160>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7957f6c241f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7957f6dbf4c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1704521446465524337, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAMbhVT4WdoA+WGjyvjVHOb4+hym+5FggPQAAAAAAAAAAM9rMvP/Olj8bV5U8X1Grvgqzb7xU8JU9AAAAAAAAAAAmce29o25MP0qElz3f7Je+XSljvF3ODrwAAAAAAAAAAGbQHD1XzlY8ZW3xvX2WML4Hwp475rBhvQAAAAAAAAAA5vQrvSkvQD6BGTw9wIA9vmyVLTwuzfO9AAAAAAAAAAAzi147hTPYuTVuELU64AIwyuuLu8uXajQAAIA/AACAPwCYIzzcOaA/UqQkPWTAk77Mms+7Wj41vQAAAAAAAAAAjYzhvQmkRj1jQeU95Sdlvs+E27vU3iK9AAAAAAAAAADNa209aGGCPTU0K73E1lO+6pe6PE+ak70AAAAAAAAAAGbMDL4AyH0/Yc67vIy6mr56q9i9aMdpPQAAAAAAAAAAwGqxPTICFj5KZcK9mghQvipSTTyIgnO9AAAAAAAAAABmo8y8H6zbuz5rvjyU+NA8CVQ+vRaqqz0AAIA/AACAPzM3LjxZiJs/uqN2PCDHjL58XoA8HiSMvAAAAAAAAAAAzbhiPgH6lj9CorE+t0Wsvm9Dgj7FFcU9AAAAAAAAAADNwlQ9lnUvPVoKJ74anU++iggJvb3JeLwAAAAAAAAAAGYm97qaFyw/ro5sve40UL5bGO+89TRfvgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_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": 248, "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "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": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:665c6f3cfb3cfdc9b28f34be0e66540b24fd387aa6ad06a2dc1747cc8c903fc9
-size 147316
+oid sha256:8ee2d9206eeb12cfe5d7bb0e9980710f9444b9bce6767fde33346e0f5196324d
+size 148068

ppo-LunarLander-v2/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 0x7b2dd83c9630>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b2dd83c96c0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b2dd83c9750>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b2dd83c97e0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7b2dd83c9870>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7b2dd83c9900>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b2dd83c9990>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b2dd83c9a20>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7b2dd83c9ab0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b2dd83c9b40>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b2dd83c9bd0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b2dd83c9c60>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7957f6c1fb50>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7957f6c1fbe0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7957f6c1fc70>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7957f6c1fd00>",
+        "_build": "<function ActorCriticPolicy._build at 0x7957f6c1fd90>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7957f6c1fe20>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7957f6c1feb0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7957f6c1ff40>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7957f6c24040>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7957f6c240d0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7957f6c24160>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7957f6c241f0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7b2dd855e840>"
+        "_abc_impl": "<_abc._abc_data object at 0x7957f6dbf4c0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -26,10 +26,13 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1704127797584510600,
+    "start_time": 1704521446465524337,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
-    "_last_obs": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
         ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
@@ -42,7 +45,7 @@
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
@@ -51,7 +54,7 @@
     "_n_updates": 248,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
-        ":serialized:": "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",
+        ":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]",
@@ -66,14 +69,14 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
         "n": "4",
         "start": "0",
         "_shape": [],
         "dtype": "int64",
         "_np_random": null
     },
-    "n_envs": 1,
+    "n_envs": 16,
     "n_steps": 1024,
     "gamma": 0.999,
     "gae_lambda": 0.98,

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57760b5c8caa353553a6dca639498d15a461635946ada6aed9ca80593bc4c8fe
-size 88490
+oid sha256:695859a985ecf3d1ce276486107ab252cbc1097c7ac4b0101e6ea48ab7c3f12e
+size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d0828af4b68eacbad2d5ad158b57841d602829efb39175948de7514371e99ca
+oid sha256:9ce4a715e5f0c6ae27667dc1671d975106a0603184cf4447a1102c4909514c7d
 size 43762

results.json

@@ -1 +1 @@
-{"mean_reward": 228.5431978, "std_reward": 62.965468887581096, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-01T17:24:42.851791"}
+{"mean_reward": 259.55178190758426, "std_reward": 14.513623690865444, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-06T06:35:24.890749"}