PPO LunarLander-v2 trained agent - batchsize 32, total_timestaps 4M

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 285.18 +/- 16.31
+      value: 276.55 +/- 18.57
       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 0x13a7439c0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x13a743a60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x13a743b00>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x13a743ba0>", "_build": "<function ActorCriticPolicy._build at 0x13a743c40>", "forward": "<function ActorCriticPolicy.forward at 0x13a743ce0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x13a743d80>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x13a743e20>", "_predict": "<function ActorCriticPolicy._predict at 0x13a743ec0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x13a743f60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x13a74c040>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x13a74c0e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x13a73b840>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 4014080, "_total_timesteps": 4000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1716120972029366000, "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": -0.0035199999999999676, "_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": 980, "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": 32, "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": "macOS-14.4.1-arm64-arm-64bit Darwin Kernel Version 23.4.0: Fri Mar 15 00:19:22 PDT 2024; root:xnu-10063.101.17~1/RELEASE_ARM64_T8112", "Python": "3.11.9", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.0", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "3.0.0", "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 0x15dc472e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x15dc47380>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x15dc47420>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x15dc474c0>", "_build": "<function ActorCriticPolicy._build at 0x15dc47560>", "forward": "<function ActorCriticPolicy.forward at 0x15dc47600>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x15dc476a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x15dc47740>", "_predict": "<function ActorCriticPolicy._predict at 0x15dc477e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x15dc47880>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x15dc47920>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x15dc479c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x15dc43040>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 4014080, "_total_timesteps": 4000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1716120972029366000, "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": -0.0035199999999999676, "_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": 980, "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": 32, "n_epochs": 4, "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": "macOS-14.4.1-arm64-arm-64bit Darwin Kernel Version 23.4.0: Fri Mar 15 00:19:22 PDT 2024; root:xnu-10063.101.17~1/RELEASE_ARM64_T8112", "Python": "3.11.9", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.0", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0141657f1c97ee69885229d75bbf221ad929200c671cb9305be1669ab0f4214
-size 147475
+oid sha256:68b3ec2f3dc2f79f625e3124b5b4832e52d99c5a132b3e5a566bba8b1a75821f
+size 147519

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 0x13a7439c0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x13a743a60>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x13a743b00>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x13a743ba0>",
-        "_build": "<function ActorCriticPolicy._build at 0x13a743c40>",
-        "forward": "<function ActorCriticPolicy.forward at 0x13a743ce0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x13a743d80>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x13a743e20>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x13a743ec0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x13a743f60>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x13a74c040>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x13a74c0e0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x15dc472e0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x15dc47380>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x15dc47420>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x15dc474c0>",
+        "_build": "<function ActorCriticPolicy._build at 0x15dc47560>",
+        "forward": "<function ActorCriticPolicy.forward at 0x15dc47600>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x15dc476a0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x15dc47740>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x15dc477e0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x15dc47880>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x15dc47920>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x15dc479c0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x13a73b840>"
+        "_abc_impl": "<_abc._abc_data object at 0x15dc43040>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -52,6 +52,21 @@
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
     "_n_updates": 980,
+    "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": 32,
+    "n_epochs": 4,
+    "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": [],
@@ -77,21 +92,6 @@
         "_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": 32,
-    "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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"

results.json

@@ -1 +1 @@
-{"mean_reward": 285.1838499, "std_reward": 16.308912752536944, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-19T17:08:59.648468"}
+{"mean_reward": 276.55158739999996, "std_reward": 18.568109969404038, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-19T17:12:03.807524"}