my first RL!

README.md

@@ -6,7 +6,7 @@ tags:
 - reinforcement-learning
 - stable-baselines3
 model-index:
-- name: PPO
+- name: PP)
   results:
   - task:
       type: reinforcement-learning
@@ -16,13 +16,13 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -419.52 +/- 135.00
+      value: 254.35 +/- 14.00
       name: mean_reward
       verified: false
 ---
 
-# **PPO** Agent playing **LunarLander-v2**
-This is a trained model of a **PPO** agent playing **LunarLander-v2**
+# **PP)** Agent playing **LunarLander-v2**
+This is a trained model of a **PP)** agent playing **LunarLander-v2**
 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
 
 ## Usage (with Stable-baselines3)

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 0x7f33ab79caf0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f33ab79cb80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f33ab79cc10>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f33ab79cca0>", "_build": "<function ActorCriticPolicy._build at 0x7f33ab79cd30>", "forward": "<function ActorCriticPolicy.forward at 0x7f33ab79cdc0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f33ab79ce50>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f33ab79cee0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f33ab79cf70>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f33ab79d000>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f33ab79d090>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f33ab79d120>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f33ab79a380>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 0.0, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1.0, "_stats_window_size": 100, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "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": 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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "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-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "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 0x7ffb09f4ab90>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ffb09f4ac20>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ffb09f4acb0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ffb09f4ad40>", "_build": "<function ActorCriticPolicy._build at 0x7ffb09f4add0>", "forward": "<function ActorCriticPolicy.forward at 0x7ffb09f4ae60>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ffb09f4aef0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ffb09f4af80>", "_predict": "<function ActorCriticPolicy._predict at 0x7ffb09f4b010>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ffb09f4b0a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ffb09f4b130>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ffb09f4b1c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ffb09f4d300>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1686797513996268308, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_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": 256, "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-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "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 sha256:01eea51cb234ddbd6732afcaecf829e44aafb6da1a5fe9db660ef5ec62e22085
-size 53848
+oid sha256:1d4478c28580eebce0a263bcf31d89fedfb8c2cd4ee6764c6df7d11f2336690d
+size 146731

ppo-LunarLander-v2/data

@@ -4,42 +4,54 @@
         ":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 0x7f33ab79caf0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f33ab79cb80>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f33ab79cc10>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f33ab79cca0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f33ab79cd30>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f33ab79cdc0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f33ab79ce50>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f33ab79cee0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f33ab79cf70>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f33ab79d000>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f33ab79d090>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f33ab79d120>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7ffb09f4ab90>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ffb09f4ac20>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ffb09f4acb0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ffb09f4ad40>",
+        "_build": "<function ActorCriticPolicy._build at 0x7ffb09f4add0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7ffb09f4ae60>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ffb09f4aef0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ffb09f4af80>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7ffb09f4b010>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ffb09f4b0a0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ffb09f4b130>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ffb09f4b1c0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f33ab79a380>"
+        "_abc_impl": "<_abc._abc_data object at 0x7ffb09f4d300>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 0,
-    "_total_timesteps": 0,
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 0.0,
+    "start_time": 1686797513996268308,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
-    "_last_obs": null,
-    "_last_episode_starts": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
+    "_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": 1.0,
+    "_current_progress_remaining": -0.015808000000000044,
     "_stats_window_size": 100,
-    "ep_info_buffer": null,
-    "ep_success_buffer": null,
-    "_n_updates": 0,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 256,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -65,14 +77,14 @@
         "_np_random": null
     },
     "n_envs": 16,
-    "n_steps": 2048,
-    "gamma": 0.99,
-    "gae_lambda": 0.95,
-    "ent_coef": 0.0,
+    "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": 10,
+    "n_epochs": 4,
     "clip_range": {
         ":type:": "<class 'function'>",
         ":serialized:": "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"

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0aa96bf78c4536c6eafd36ce78653aac56f76c12f489666d21b1ace601e8300
-size 687
+oid sha256:c8250d4cc87548f789371ad5255c70b1b418e43b83b683d57e3d127d68025daf
+size 87929

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ef9d8e1be881b8d286a3b8a49e7e689803773d125d2a27a04664b9805295e02
+oid sha256:dbca7d55e4f09d5f8288816716aa1a13d4758d55d67694bd52bd2eaf1d4ba4da
 size 43329

results.json

@@ -1 +1 @@
-{"mean_reward": -419.51632069999994, "std_reward": 135.00435213310223, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-15T01:31:33.381621"}
+{"mean_reward": 254.3466469, "std_reward": 14.004343613271107, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-15T03:12:09.908714"}