Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 278.82 +/- 11.26
+      value: 284.51 +/- 17.72
       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 0x7fd3f35b4940>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd3f35b49d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd3f35b4a60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd3f35b4af0>", "_build": "<function ActorCriticPolicy._build at 0x7fd3f35b4b80>", "forward": "<function ActorCriticPolicy.forward at 0x7fd3f35b4c10>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fd3f35b4ca0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd3f35b4d30>", "_predict": "<function ActorCriticPolicy._predict at 0x7fd3f35b4dc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd3f35b4e50>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd3f35b4ee0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd3f35b4f70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fd3f35ae180>"}, "verbose": 2, "policy_kwargs": {}, "num_timesteps": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1748424223338010293, "learning_rate": 0.0003, "tensorboard_log": "./ppo_logs/", "_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": 984, "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": 1024, "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": 8, "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-5.15.153.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Fri Mar 29 23:14:13 UTC 2024", "Python": "3.10.14", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.0+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.1", "Gymnasium": "0.28.1"}}
+{"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 0x7fd3f35b4940>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd3f35b49d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd3f35b4a60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd3f35b4af0>", "_build": "<function ActorCriticPolicy._build at 0x7fd3f35b4b80>", "forward": "<function ActorCriticPolicy.forward at 0x7fd3f35b4c10>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fd3f35b4ca0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd3f35b4d30>", "_predict": "<function ActorCriticPolicy._predict at 0x7fd3f35b4dc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd3f35b4e50>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd3f35b4ee0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd3f35b4f70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fd3f35ae180>"}, "verbose": 2, "policy_kwargs": {}, "num_timesteps": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1748424223338010293, "learning_rate": 0.0, "tensorboard_log": "./ppo_logs/", "_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": 984, "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": 128, "n_epochs": 8, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "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": 16, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.153.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Fri Mar 29 23:14:13 UTC 2024", "Python": "3.10.14", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.0+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.1", "Gymnasium": "0.28.1"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcd2b1c33bbc28a84ebceb2df07b831816f9e86d15669466dd9237555dd29e94
-size 148024
+oid sha256:6a44f4d4d1153465ab38eb3ad9391591d8cd552ecdab6d584c1855bf3bed7761
+size 147813

ppo-LunarLander-v2/data

@@ -27,7 +27,7 @@
     "seed": null,
     "action_noise": null,
     "start_time": 1748424223338010293,
-    "learning_rate": 0.0003,
+    "learning_rate": 0.0,
     "tensorboard_log": "./ppo_logs/",
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -52,6 +52,21 @@
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
     "_n_updates": 984,
+    "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": 128,
+    "n_epochs": 8,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -69,7 +84,7 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
+        ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
         "n": "4",
         "start": "0",
         "_shape": [],
@@ -77,23 +92,8 @@
         "_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": 128,
-    "n_epochs": 8,
-    "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 sha256:82457528eef40d93aaaaa23442e7bb18e30f0648b5a257347c7dee222abbc1dc
-size 88362
+oid sha256:8706d068bae37fa4711777783fb0e47689170e50be38275f8e1592d75cf0d313
+size 88490

results.json

@@ -1 +1 @@
-{"mean_reward": 278.81712972943706, "std_reward": 11.258328199308389, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-05-28T20:19:14.765191"}
+{"mean_reward": 284.5147661249216, "std_reward": 17.72155301148973, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-05-28T22:04:50.547855"}