the RL tutorial from HF using PPO

README.md

@@ -6,7 +6,7 @@ tags:
 - reinforcement-learning
 - stable-baselines3
 model-index:
-- name: MLP-PPO
+- name: PPO
   results:
   - task:
       type: reinforcement-learning
@@ -16,13 +16,13 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -109.85 +/- 116.42
+      value: 255.12 +/- 18.16
       name: mean_reward
       verified: false
 ---
 
-# **MLP-PPO** Agent playing **LunarLander-v2**
-This is a trained model of a **MLP-PPO** agent playing **LunarLander-v2**
+# **PPO** Agent playing **LunarLander-v2**
+This is a trained model of a **PPO** 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 0x7919d3922b00>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7919d3922b90>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7919d3922c20>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7919d3922cb0>", "_build": "<function ActorCriticPolicy._build at 0x7919d3922d40>", "forward": "<function ActorCriticPolicy.forward at 0x7919d3922dd0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7919d3922e60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7919d3922ef0>", "_predict": "<function ActorCriticPolicy._predict at 0x7919d3922f80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7919d3923010>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7919d39230a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7919d3923130>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7919d38b9500>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 200704, "_total_timesteps": 200000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1701286072697374815, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAHMKf74fyXg/cnBuvS9teb4DwJO9EJqVvAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": 784, "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": 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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu118", "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 0x7919d3922b00>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7919d3922b90>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7919d3922c20>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7919d3922cb0>", "_build": "<function ActorCriticPolicy._build at 0x7919d3922d40>", "forward": "<function ActorCriticPolicy.forward at 0x7919d3922dd0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7919d3922e60>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7919d3922ef0>", "_predict": "<function ActorCriticPolicy._predict at 0x7919d3922f80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7919d3923010>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7919d39230a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7919d3923130>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7919d38b9500>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1701286661869302767, "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": 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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "system_info": {"OS": "Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu118", "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 sha256:9497f5dab670a316bf73cecbf0c241a5a1a15a0bb2949086cad6476637391ea8
-size 147388
+oid sha256:aad3fca9e144a6041ea0416f0a8baf39b24d4c47d0ab3b1ef0fef8a727551013
+size 148050

ppo-LunarLander-v2/data

@@ -21,37 +21,37 @@
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 200704,
-    "_total_timesteps": 200000,
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1701286072697374815,
+    "start_time": 1701286661869302767,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAHMKf74fyXg/cnBuvS9teb4DwJO9EJqVvAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
     },
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.0035199999999999676,
+    "_current_progress_remaining": -0.015808000000000044,
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "gAWVQAwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHIDnpGFzuGMAWyUTTkBjAF0lEdAlBaHYL9deXV9lChoBkdAayr3W4EwFmgHTSwBaAhHQJQXCtihFmZ1fZQoaAZHQG3Km0NSZShoB01QAWgIR0CUF2OyVv/BdX2UKGgGR0Bw08Kmbb1zaAdNQwFoCEdAlBhPo/zJ63V9lChoBkdAcOtcvduYQmgHTUUBaAhHQJQYuWldkax1fZQoaAZHQHDUktI065poB00tAWgIR0CUGpCL/CIldX2UKGgGR0ByVQB3iaRZaAdNLgFoCEdAlBsqguh9LHV9lChoBkdAcg6trsSkCWgHTRsBaAhHQJQbZknTiKl1fZQoaAZHQHCh3V09yLhoB03rAWgIR0CUHATwlSjydX2UKGgGR0ByFFvze40/aAdNJAFoCEdAlB1lIZqEe3V9lChoBkdAcNW91EE1VGgHTWEBaAhHQJQdyCrcTJ11fZQoaAZHQHEYkl/pdKNoB00xAWgIR0CUHsGyX2M9dX2UKGgGR0BtZqmj0tiAaAdNJAFoCEdAlB7mj9GZu3V9lChoBkdAbDXW0Z3s5WgHTZUBaAhHQJQfAUL2HtZ1fZQoaAZHQHJo1OsT37FoB00mAWgIR0CUH3dIXj2jdX2UKGgGR0BxsxMj/uLKaAdNQgFoCEdAlCCBEF4cFXV9lChoBkdAclorCm/Fi2gHTTgBaAhHQJQhHyRSxaB1fZQoaAZHQHAK118stkFoB000AWgIR0CUIXXb/Ot5dX2UKGgGR0BxdyOS4e90aAdNSAFoCEdAlCJvgNwzcnV9lChoBkdAb8mQVbiZOWgHTS4BaAhHQJQieZNO/L11fZQoaAZHQG0GotthuwZoB00kAWgIR0CUJRI3R5TqdX2UKGgGR0Bw0D1kDp1SaAdNMQFoCEdAlCVTJMg2ZXV9lChoBkdAcZJqrilzl2gHTTABaAhHQJQmGjua4MF1fZQoaAZHQHD/KBy0a61oB01qAWgIR0CUJsqt5le4dX2UKGgGR0Bv+PfXPJJYaAdNLQFoCEdAlCdqmXPZ7HV9lChoBkdAboOBFNL13GgHTTABaAhHQJQn5fhMrVh1fZQoaAZHQHDZUM9bHIZoB00yAWgIR0CUKRBqKxcFdX2UKGgGR0BvoY371qWUaAdNLwFoCEdAlCkYcWCVbHV9lChoBkdAbUnf0Eovz2gHTSsBaAhHQJQpmIGhVVB1fZQoaAZHQHEbq0hNdqtoB008AWgIR0CUKaHMEA5rdX2UKGgGR0BkcjyxzJZGaAdNBgJoCEdAlCpfpt78enV9lChoBkdAculwgkka/GgHTUUBaAhHQJQsDjBEa2p1fZQoaAZHQHIHsKCxu89oB01fAWgIR0CULFBRAKOUdX2UKGgGR0BJfqNIbwSbaAdL1WgIR0CULH08eS0TdX2UKGgGR0BvguGVRk3CaAdNNgFoCEdAlCzqHTI/7nV9lChoBkdAcdfXXyy2QWgHTTsBaAhHQJQtG3nZCfJ1fZQoaAZHQEz/RZ2ZAptoB0vQaAhHQJQtNeNT9891fZQoaAZHQG0xZlWfbsZoB00hAWgIR0CULw6iCaqkdX2UKGgGR0Br+PmYBvJjaAdNqQFoCEdAlC+LcfvF33V9lChoBkdAcEzajvd/KGgHTScBaAhHQJQxLyjHn2Z1fZQoaAZHQG+i48U21lZoB00+AWgIR0CUMnCPp6hQdX2UKGgGR0Bv8abayrxRaAdNaQFoCEdAlDLrMLWqcXV9lChoBkdAbXb0btJFs2gHTSIBaAhHQJQzCkbgjyF1fZQoaAZHQHCRfJzT4L1oB00hAWgIR0CUMwr6LwWndX2UKGgGR0BwrQbDMvAXaAdNNwFoCEdAlDMyprDZUXV9lChoBkdAcfjbr1M/QmgHTT0BaAhHQJQzX6Ggzxh1fZQoaAZHQHAl/lhgE2ZoB00tAWgIR0CUNAUSZjQRdX2UKGgGR0Bwhjs2NvOyaAdNHAFoCEdAlEs1wHZ9NXV9lChoBkdARDxaX8fmtGgHTR0BaAhHQJRLrzmOlwd1fZQoaAZHQHGzixA0KqpoB00vAWgIR0CUTJm0E5hjdX2UKGgGR0BwAOBAfMfSaAdNOQFoCEdAlEzORgZ0jnV9lChoBkdAcUazLfUF0WgHTWYBaAhHQJRNOeAd4ml1fZQoaAZHQHB2A8SwnploB01vAWgIR0CUTbKWszVMdX2UKGgGR0BwwI8RtgrpaAdNRgFoCEdAlE86H9FWn3V9lChoBkdAcFb+d9Ujs2gHTUIBaAhHQJRPmtGNJe51fZQoaAZHQE8QCrcTJyRoB0vhaAhHQJRPufg75mB1fZQoaAZHQG6gxqfvnbJoB00vAWgIR0CUUbusLfDUdX2UKGgGR0BtGUnCwbEQaAdNGwFoCEdAlFHQDJU5uXV9lChoBkdAcxrejmCAc2gHTSkBaAhHQJRR+paRp111fZQoaAZHQHAwlo11nuloB01BAWgIR0CUUtyFPBSDdX2UKGgGR0BrIZbKRuCPaAdNIwFoCEdAlFML5RCQcXV9lChoBkdAcFJu8scyWWgHTUgBaAhHQJRTddt2s7x1fZQoaAZHQG/MWa2F36hoB00iAWgIR0CUVI3TNMXadX2UKGgGR0BzNO5mRNh3aAdNDgFoCEdAlFVVEy+HrXV9lChoBkdAcO64vN/vv2gHTQ0BaAhHQJRWgKqn3td1fZQoaAZHQHEOAdsBQvZoB00hAWgIR0CUVqPE87p3dX2UKGgGR0Bo2D/dZaFFaAdN/gFoCEdAlFdVSXMQmXV9lChoBkdAcFhc0+C9RWgHTUsBaAhHQJRXjDm8ujB1fZQoaAZHQHGPEk8ifQNoB00cAWgIR0CUWMtIkJKKdX2UKGgGR0Bw/bHggow3aAdNIwFoCEdAlFkh6nivPnV9lChoBkdAcwq9K28Zk2gHTUwBaAhHQJRaBVuJk5J1fZQoaAZHQHI6nB1s+FFoB00YAWgIR0CUWuOvt+kQdX2UKGgGR0BwvIt+TeO5aAdN2AFoCEdAlFr+RHPNV3V9lChoBkdAcpCfYSQHRmgHTSUBaAhHQJRbN5LRKHx1fZQoaAZHQHBc7Io3JgdoB00mAWgIR0CUXGYxcmjTdX2UKGgGR0BvBTAUL2HtaAdNXQFoCEdAlF1Zswco6XV9lChoBkdAcA6UJOWSlmgHTUUBaAhHQJRdsD/2kBV1fZQoaAZHQHCupUkv9LpoB00HAWgIR0CUXfaP0Zm7dX2UKGgGR0BxDZwwTM7maAdNQwFoCEdAlF4L1mJ3xHV9lChoBkdAclXgOz6acGgHTVEBaAhHQJRffg4wRGt1fZQoaAZHQG+AfhVENONoB00ZAWgIR0CUYEuxrzoVdX2UKGgGR0BPhF90A93baAdL4WgIR0CUYGOoHcDbdX2UKGgGR0BuzRtJnQIEaAdNPAFoCEdAlGCSsXBP9HV9lChoBkdAcoqkGzKLbmgHTT0BaAhHQJRguF/QSjB1fZQoaAZHQHJzK8+RoytoB01MAWgIR0CUYfEKE385dX2UKGgGR0BvyBCY1He8aAdNLQFoCEdAlGI8Aq/dqXV9lChoBkdAb6X5E+gUUWgHTRkBaAhHQJRiwCKaXrt1fZQoaAZHQGsTyOR1X/5oB000AWgIR0CUZLEkSmIkdX2UKGgGR0BwEL6DXe3yaAdNPgFoCEdAlGT5+tr9EXV9lChoBkdAcP7UWl/H52gHTTYBaAhHQJRlFzxPO6d1fZQoaAZHQG5pYU34sVdoB00RAWgIR0CUZgSRr8BNdX2UKGgGR0BxRIk5ZKWcaAdNCQFoCEdAlGYPqX4TK3V9lChoBkdAbk7Ba9sabWgHTRMBaAhHQJRmqrvLHMl1fZQoaAZHQHAW6MFUyYZoB01YAWgIR0CUZ3RHww0wdX2UKGgGR0BwfyVD8cdYaAdNMAFoCEdAlGe5H/cWTHV9lChoBkdAa320KJEYwmgHTSMBaAhHQJRo2yAxzq91fZQoaAZHQHGh76k6901oB00lAWgIR0CUai9jgAIZdX2UKGgGR0BuJUSZjQRgaAdNNwFoCEdAlGqefI0ZWXV9lChoBkdAcL3ZflZHNGgHTTkBaAhHQJRq2fAbhm51fZQoaAZHQHBhMh5gPVdoB01FAWgIR0CUa9HtF8XvdWUu"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 784,
+    "_n_updates": 248,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -76,7 +76,7 @@
         "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 sha256:296814058c8c9bf0b10097e7cbc9f1ee0e4dd61ea9e2c626cc356ca819884163
+oid sha256:0d2bebca3b10fd8bd2ef64d543cfd4762e663b2eee92794967cada567c34bfe7
 size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:716bd6c4ea46bbcc44d63a1546606a3636312253c6873a7e0b49cdcf43919db9
+oid sha256:c0994bc1c58b869afa5469ca114fd3d6a77a14e41372bd1463ac62533cd97969
 size 43762

results.json

@@ -1 +1 @@
-{"mean_reward": -109.8521327, "std_reward": 116.42212125443554, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-29T19:35:37.910684"}
+{"mean_reward": 255.11884029999996, "std_reward": 18.155994372406482, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-11-29T20:00:50.080386"}