First version of PPO LunarLander-v2

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -242.30 +/- 152.89
+      value: 191.22 +/- 42.60
       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 0x79107c626700>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x79107c6267a0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x79107c626840>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x79107c6268e0>", "_build": "<function ActorCriticPolicy._build at 0x79107c626980>", "forward": "<function ActorCriticPolicy.forward at 0x79107c626a20>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x79107c626ac0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x79107c626b60>", "_predict": "<function ActorCriticPolicy._predict at 0x79107c626c00>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x79107c626ca0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x79107c626d40>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x79107c626de0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x79107c7a7700>"}, "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:": "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": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWV1gIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwiVAZcAiQFTAJROhZQpjAFflIWUjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjExL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUS4RDCPiAANgPEogKlEMAlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTEvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpRoAIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCF9lH2UKGgYjARmdW5jlIwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBmMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP8mZmZmZmZqFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="}, "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": "3.11.11", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.5.1+cu124", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.1", "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 0x79107c626700>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x79107c6267a0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x79107c626840>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x79107c6268e0>", "_build": "<function ActorCriticPolicy._build at 0x79107c626980>", "forward": "<function ActorCriticPolicy.forward at 0x79107c626a20>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x79107c626ac0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x79107c626b60>", "_predict": "<function ActorCriticPolicy._predict at 0x79107c626c00>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x79107c626ca0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x79107c626d40>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x79107c626de0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x79107c7a7700>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1007616, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1740031717368368719, "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": 0.99, "gae_lambda": 0.95, "ent_coef": 0.005, "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:": "gAWV1gIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwiVAZcAiQFTAJROhZQpjAFflIWUjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjExL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUS4RDCPiAANgPEogKlEMAlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTEvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpRoAIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCF9lH2UKGgYjARmdW5jlIwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBmMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHPzOpKjBVMmGFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="}, "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": "3.11.11", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.5.1+cu124", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.1", "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:e33c50d1b1265954b02e14b45fa9cd0cc575c694ff35f56d6b2f7a9d78dc2a54
-size 55226
+oid sha256:162699923ad59fecec8e9f07b1b678ad5d39ad8af77375a68147622072e74007
+size 148134

ppo-LunarLander-v2/data

@@ -21,25 +21,37 @@
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 0,
-    "_total_timesteps": 0,
+    "num_timesteps": 1007616,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 0.0,
+    "start_time": 1740031717368368719,
     "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": -0.007616000000000067,
     "_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": 1230,
     "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": 1024,
-    "gamma": 0.999,
-    "gae_lambda": 0.98,
-    "ent_coef": 0.01,
+    "n_steps": 512,
+    "gamma": 0.99,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.005,
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
-    "batch_size": 64,
-    "n_epochs": 4,
+    "batch_size": 128,
+    "n_epochs": 10,
     "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 sha256:13dbf41e305d3a0b52e13b973ece0bb28ffca5bcf57636bcf9b68102feec544e
-size 1120
+oid sha256:648dd9b7e9f05552c6524b821fd2e0178f9b0ae782e4fa517af08d9ba05abdfe
+size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fe0b578e10f661adc988c475e9be9e607563a69d806383d610df009fa7b27d0
+oid sha256:c71937fe7013901bf3d89cca99108fa98a15ea2e3b8d0c4795de6a9b0ade3ba1
 size 43762

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fc50b8586d97a265222d3a5da289dc077c6acb45158f987efdef76ea1d69613
-size 210915
+oid sha256:0a2bed69fa5c2aa47436abe62e8db71387fef007a4bc74144811156319887f6b
+size 168156

results.json

@@ -1 +1 @@
-{"mean_reward": -242.30282900000003, "std_reward": 152.8868970848728, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-20T06:05:57.516208"}
+{"mean_reward": 191.2150276, "std_reward": 42.595660274937735, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-20T06:31:24.117130"}