Update

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -307.05 +/- 34.46
+      value: 269.93 +/- 50.33
       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 0x7cf596c03740>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7cf596c037e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7cf596c03880>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7cf596c03920>", "_build": "<function ActorCriticPolicy._build at 0x7cf596c039c0>", "forward": "<function ActorCriticPolicy.forward at 0x7cf596c03a60>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7cf596c03b00>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7cf596c03ba0>", "_predict": "<function ActorCriticPolicy._predict at 0x7cf596c03c40>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7cf596c03ce0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7cf596c03d80>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7cf596c03e20>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7cf596d66a00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 100352, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1738159904398105862, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAOrF5z5i/ry9alnZPWoDUDu5fgS+G5fSPQAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": 392, "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": 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:": "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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": "3.11.11", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.5.1+cu121", "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 0x7cf596c03740>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7cf596c037e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7cf596c03880>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7cf596c03920>", "_build": "<function ActorCriticPolicy._build at 0x7cf596c039c0>", "forward": "<function ActorCriticPolicy.forward at 0x7cf596c03a60>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7cf596c03b00>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7cf596c03ba0>", "_predict": "<function ActorCriticPolicy._predict at 0x7cf596c03c40>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7cf596c03ce0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7cf596c03d80>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7cf596c03e20>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7cf596d66a00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 3147870, "_total_timesteps": 100000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1738160834920808054, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAOY4hT6PoFq8a0INvhp0HD2l0gi/6lGlvwAAgD8AAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": 0.96852224, "_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": 12296, "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": 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:": "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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": "3.11.11", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.5.1+cu121", "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 sha256:73aeac35b5dc961b9ec93dacaba58f45b4270ae125288fa6f259bdaf1fb71e99
-size 147386
+oid sha256:c2e32855b1227dcc0c7dcb8a1a17fb400bfb5a4bd8bcbe5981998e0b2b2aba55
+size 147348

ppo-LunarLander-v2/data

@@ -21,17 +21,17 @@
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 100352,
-    "_total_timesteps": 100000,
+    "num_timesteps": 3147870,
+    "_total_timesteps": 100000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1738159904398105862,
+    "start_time": 1738160834920808054,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAOrF5z5i/ry9alnZPWoDUDu5fgS+G5fSPQAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAOY4hT6PoFq8a0INvhp0HD2l0gi/6lGlvwAAgD8AAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -41,17 +41,17 @@
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.0035199999999999676,
+    "_current_progress_remaining": 0.96852224,
     "_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": 392,
+    "_n_updates": 12296,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c0a4e8df429309d022e39f0a5c89025183a6fb5cfba2275c3855c772578632a
+oid sha256:be545b3f2219750cd39208f4cc1d634df81f323020ac34557d4c3c0f4756d7d3
 size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fa46f31e174593ab1e350b811e39ede02f16fc09d418c31d9237e2ee239caf5
+oid sha256:1fe78a1d7a90f229a5feb497e072a648fa025c4d767638413f3122ccb2fcf503
 size 43762

results.json

@@ -1 +1 @@
-{"mean_reward": -307.0518427, "std_reward": 34.45606205260157, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-29T14:25:53.468366"}
+{"mean_reward": 269.92874390000003, "std_reward": 50.32698412588608, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-29T15:59:38.004398"}