PPO commit

README.md

@@ -6,7 +6,7 @@ tags:
 - reinforcement-learning
 - stable-baselines3
 model-index:
-- name: A2C
+- name: PPO
   results:
   - task:
       type: reinforcement-learning
@@ -16,13 +16,13 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -2560.60 +/- 631.35
+      value: 283.10 +/- 21.94
       name: mean_reward
       verified: false
 ---
 
-# **A2C** Agent playing **LunarLander-v2**
-This is a trained model of a **A2C** 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 0x7e4b7d828430>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e4b7d8284c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e4b7d828550>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e4b7d8285e0>", "_build": "<function ActorCriticPolicy._build at 0x7e4b7d828670>", "forward": "<function ActorCriticPolicy.forward at 0x7e4b7d828700>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e4b7d828790>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e4b7d828820>", "_predict": "<function ActorCriticPolicy._predict at 0x7e4b7d8288b0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e4b7d828940>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e4b7d8289d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e4b7d828a60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e4b1f10fc40>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "num_timesteps": 501760, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1730713089689435431, "learning_rate": 0.0007, "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": -0.0035199999999999676, "_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": 245, "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": 16, "n_steps": 128, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "normalize_advantage": true, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.5.0+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.0", "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 0x7e4b7d828430>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e4b7d8284c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e4b7d828550>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e4b7d8285e0>", "_build": "<function ActorCriticPolicy._build at 0x7e4b7d828670>", "forward": "<function ActorCriticPolicy.forward at 0x7e4b7d828700>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e4b7d828790>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e4b7d828820>", "_predict": "<function ActorCriticPolicy._predict at 0x7e4b7d8288b0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e4b7d828940>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e4b7d8289d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e4b7d828a60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e4b1f10fc40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1007616, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1730713480713648672, "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": -0.007616000000000067, "_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": 1230, "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": 16, "n_steps": 512, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 128, "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-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.5.0+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.0", "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:c8e9ef8e1ca9e5757adad27097d8bb2908368c1e1120f69927e1601b11de5df2
-size 104957
+oid sha256:c44df8fd47ec8f4ae21661974b220da352d9801e251a3617e028f9eb04981e90
+size 147902

ppo-LunarLander-v2/data

@@ -20,27 +20,18 @@
         "_abc_impl": "<_abc._abc_data object at 0x7e4b1f10fc40>"
     },
     "verbose": 1,
-    "policy_kwargs": {
-        ":type:": "<class 'dict'>",
-        ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=",
-        "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>",
-        "optimizer_kwargs": {
-            "alpha": 0.99,
-            "eps": 1e-05,
-            "weight_decay": 0
-        }
-    },
-    "num_timesteps": 501760,
-    "_total_timesteps": 500000,
+    "policy_kwargs": {},
+    "num_timesteps": 1007616,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1730713089689435431,
-    "learning_rate": 0.0007,
+    "start_time": 1730713480713648672,
+    "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -50,17 +41,17 @@
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.0035199999999999676,
+    "_current_progress_remaining": -0.007616000000000067,
     "_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'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 245,
+    "_n_updates": 1230,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -86,15 +77,23 @@
         "_np_random": null
     },
     "n_envs": 16,
-    "n_steps": 128,
+    "n_steps": 512,
     "gamma": 0.999,
     "gae_lambda": 0.98,
     "ent_coef": 0.01,
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
+    "batch_size": 128,
+    "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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"
+        ":serialized:": "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"
     }
 }

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bfed629206dd72aa8b8272b0b531ff3623b9dd6a6937ab33255991f778d7400
-size 46094
+oid sha256:4397ac2d786ac57ee2092e88e21c3b2ba472be135afde1968b368b769e331ed0
+size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:431676284422eec4317cb6579f556aa05e028501a3f264e2b2f601d1ed8e2352
+oid sha256:98751bfd78558f3e7ba14648680c8cca19e75291e2bb0fdbbe2b8df9bff2efaf
 size 43762

results.json

@@ -1 +1 @@
-{"mean_reward": -2560.5956805, "std_reward": 631.350590441782, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-04T09:40:52.654262"}
+{"mean_reward": 283.10213239999996, "std_reward": 21.935219116895382, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-04T10:01:58.275665"}