first try

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: stable-baselines3
 tags:
-- LunarLander-v2
+- LunarLander-v3
 - deep-reinforcement-learning
 - reinforcement-learning
 - stable-baselines3
@@ -12,17 +12,17 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: LunarLander-v2
-      type: LunarLander-v2
+      name: LunarLander-v3
+      type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 258.14 +/- 21.61
+      value: 258.77 +/- 15.52
       name: mean_reward
       verified: false
 ---
 
-# **PPO** Agent playing **LunarLander-v2**
-This is a trained model of a **PPO** agent playing **LunarLander-v2**
+# **PPO** Agent playing **LunarLander-v3**
+This is a trained model of a **PPO** agent playing **LunarLander-v3**
 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 0x7aee29816200>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7aee29816290>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7aee29816320>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7aee298163b0>", "_build": "<function ActorCriticPolicy._build at 0x7aee29816440>", "forward": "<function ActorCriticPolicy.forward at 0x7aee298164d0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7aee29816560>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7aee298165f0>", "_predict": "<function ActorCriticPolicy._predict at 0x7aee29816680>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7aee29816710>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7aee298167a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7aee29816830>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7aedcb4e69c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1736079514409023247, "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": -0.015808000000000044, "_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": 310, "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": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "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:": "gAWVrQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUaACMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFowEZnVuY5SMDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "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": "2.5.1+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 0x7fa9630ed440>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa9630ed4e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa9630ed580>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa9630ed620>", "_build": "<function ActorCriticPolicy._build at 0x7fa9630ed6c0>", "forward": "<function ActorCriticPolicy.forward at 0x7fa9630ed760>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fa9630ed800>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa9630ed8a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fa9630ed940>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa9630ed9e0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa9630eda80>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa9630edb20>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fa963327200>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1736090042075663743, "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": -0.015808000000000044, "_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": 248, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[ -2.5        -2.5       -10.        -10.         -6.2831855 -10.\n  -0.         -0.       ]", "bounded_below": "[ True  True  True  True  True  True  True  True]", "high": "[ 2.5        2.5       10.        10.         6.2831855 10.\n  1.         1.       ]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "low_repr": "[ -2.5        -2.5       -10.        -10.         -6.2831855 -10.\n  -0.         -0.       ]", "high_repr": "[ 2.5        2.5       10.        10.         6.2831855 10.\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, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}", "__doc__": "\n    Rollout buffer used in on-policy algorithms like A2C/PPO.\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to classic advantage when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ", "__init__": "<function RolloutBuffer.__init__ at 0x7fa96303e3e0>", "reset": "<function RolloutBuffer.reset at 0x7fa96303e480>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7fa96303e520>", "add": "<function RolloutBuffer.add at 0x7fa96303e660>", "get": "<function RolloutBuffer.get at 0x7fa96303e700>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7fa96303e7a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fa9633e6e80>"}, "rollout_buffer_kwargs": {}, "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-5.15.167.4-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Tue Nov 5 00:21:55 UTC 2024", "Python": "3.12.2", "Stable-Baselines3": "2.4.0", "PyTorch": "2.5.1+cu124", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.0", "Gymnasium": "1.0.0"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ec529e9f24320ed6a2ed65a11f74830071021b5add9a57bcbe34911a33937b6
-size 147939
+oid sha256:99be5f75be8422a1c93cfdb2bda647f676dbbf97a970210eee2ebc601ba3df92
+size 151426

ppo-LunarLander-v2/_stable_baselines3_version

@@ -1 +1 @@
-2.0.0a5
+2.4.0

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 0x7aee29816200>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7aee29816290>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7aee29816320>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7aee298163b0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7aee29816440>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7aee298164d0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7aee29816560>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7aee298165f0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7aee29816680>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7aee29816710>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7aee298167a0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7aee29816830>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fa9630ed440>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa9630ed4e0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa9630ed580>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa9630ed620>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fa9630ed6c0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fa9630ed760>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fa9630ed800>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa9630ed8a0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fa9630ed940>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa9630ed9e0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa9630eda80>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa9630edb20>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7aedcb4e69c0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fa963327200>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -26,12 +26,12 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1736079514409023247,
+    "start_time": 1736090042075663743,
     "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'>",
@@ -45,26 +45,26 @@
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "gAWVMgwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQGywa0x/NJSMAWyUTUkBjAF0lEdAkGGMyBTXKHV9lChoBkdAcoGXvH93r2gHTQMBaAhHQJBh+puMuOF1fZQoaAZHQHHOo+bExZdoB00IAWgIR0CQYjWd3B55dX2UKGgGR0BvA90gbIcSaAdNNwFoCEdAkGKoQnQY13V9lChoBkdAcrKzGxUvPGgHTTABaAhHQJBjR+OOsDJ1fZQoaAZHQHDBWwiaAnVoB0vuaAhHQJBjUsYl6Z91fZQoaAZHQHD0VYhdMTNoB00JAWgIR0CQY10voNd7dX2UKGgGR0Bw5dJnQID6aAdNDwFoCEdAkGOfCAMDwHV9lChoBkdAcSYRoh6jWWgHS/RoCEdAkGQ9elbeM3V9lChoBkdAcUTApazNU2gHTSQBaAhHQJBkUPrfLs91fZQoaAZHQG5GMXrMTvloB00OAWgIR0CQZGlruYx+dX2UKGgGR0BwcZF9a2WqaAdNQwFoCEdAkGVnnZCfH3V9lChoBkdAbJ63WFvhqGgHTQUBaAhHQJBlzDIikft1fZQoaAZHQHDtlSKm8/VoB00iAWgIR0CQZ9nYQJ5WdX2UKGgGR0Bw/p2s7uD0aAdNEwFoCEdAkGhI/zJ6p3V9lChoBkdAcjQopx3mm2gHS/1oCEdAkGh694/u9nV9lChoBkdAccSYD1XeWWgHTQcBaAhHQJBpAC6pYLd1fZQoaAZHQG5hAlWwNb1oB01GAWgIR0CQaZNZvDP4dX2UKGgGR0BwczDuSfUXaAdNOgFoCEdAkGnQEU0vXnV9lChoBkdAcl3SZ0CA+mgHTRoBaAhHQJBp/pu/Dcd1fZQoaAZHQHIYImXw9aFoB00ZAWgIR0CQap4UN8VpdX2UKGgGR0Bvzn36AOJ+aAdNEgFoCEdAkGq40qH45HV9lChoBkdAcBs7j1f3OGgHTS0BaAhHQJBrC/k/8l51fZQoaAZHQHE3Uh7mdRRoB00KAWgIR0CQazHim2srdX2UKGgGR0BvddRiw0O3aAdNHgFoCEdAkGvE3Kji43V9lChoBkdAc1TP2f02+GgHTRsBaAhHQJBryuieumt1fZQoaAZHQHIXmkJrtVtoB0vyaAhHQJBrzm3fAKx1fZQoaAZHQHAMGqo60Y1oB01gAWgIR0CQbElA/s3RdX2UKGgGR0BwxdqveP7vaAdNKQFoCEdAkG1nR9gF5nV9lChoBkdAchaYgJTl1mgHTQMBaAhHQJBuXYI0IkZ1fZQoaAZHQG8OFO45Lh9oB0v9aAhHQJBu0Ht4RmN1fZQoaAZHQHEdoHs1KoRoB0vraAhHQJBu1+nZTQ51fZQoaAZHQHC7zPjXFtNoB00ZAWgIR0CQcKX4CZF5dX2UKGgGR0BtU2N96TnraAdNEgFoCEdAkHC0j1PFenV9lChoBkdAbsIx3V09yWgHTQwBaAhHQJBwvUMG5c11fZQoaAZHQHBjPdEb5uZoB01MAWgIR0CQcNnDR+jNdX2UKGgGR0BzBgKIBRyfaAdNHgFoCEdAkHHh6nivPnV9lChoBkdAcNy1dPci4mgHTR4BaAhHQJByV4RmK651fZQoaAZHQHAlKQRwqAloB00GAWgIR0CQcn4VymygdX2UKGgGR0Bw3RV0cOslaAdL9WgIR0CQcqXf642CdX2UKGgGR0BxgJUJfICEaAdNRgFoCEdAkHMNAHE/B3V9lChoBkdAbypkQwsXi2gHTSABaAhHQJBzI78vVVh1fZQoaAZHQHCMSlSCOFRoB007AWgIR0CQczvSMLncdX2UKGgGR0Bs91wFTvRaaAdNIgFoCEdAkHM5bQkX13V9lChoBkdAciGog3cYZWgHTRoBaAhHQJB0ohLXcxl1fZQoaAZHQHF/XyAhB7hoB00QAWgIR0CQljSEUTL4dX2UKGgGR0Bzku5uqFRHaAdL22gIR0CQlxVKf4ATdX2UKGgGR0BzgAZNwiqyaAdL/WgIR0CQl9Tq0MPSdX2UKGgGR0BwbSq94/u9aAdL/GgIR0CQl97mdRR/dX2UKGgGR0BwGvmEGqxUaAdNQgFoCEdAkJf15v99+nV9lChoBkdAch+t52QnyGgHTVgBaAhHQJCYbMKTjed1fZQoaAZHQG/pyK3uuzRoB00dAWgIR0CQmKY+Sr5qdX2UKGgGR0Bxf5JYkmhNaAdL9GgIR0CQmWIVuaWpdX2UKGgGR0BuOMOoYNy6aAdNEAFoCEdAkJlf38GcF3V9lChoBkdAcoVx6OYIB2gHTQMBaAhHQJCZee/YapB1fZQoaAZHQHE6NA9mpVFoB00TAWgIR0CQmjJtBOYZdX2UKGgGR0BygbBGhEjPaAdNAQFoCEdAkJpSZv1lG3V9lChoBkdAbg3PHDJlrmgHTSIBaAhHQJCbbKzRhMJ1fZQoaAZHQGxba4+bExZoB01MAWgIR0CQnIpQDV6NdX2UKGgGR0BxwSDUVi4KaAdNTgFoCEdAkJytgKF7D3V9lChoBkdAcQbc0tRNy2gHTRcBaAhHQJCc26Ymb9Z1fZQoaAZHQG7soDYAbQ1oB00nAWgIR0CQngXw9aEBdX2UKGgGR0BwhKTUy57PaAdNIwFoCEdAkJ7sNhE0BXV9lChoBkdAcR7oOhCdBmgHTRsBaAhHQJCfn4WUKRd1fZQoaAZHQHBPX62v0RRoB00SAWgIR0CQoCgydnTRdX2UKGgGR0BwvFid8RcvaAdNMQFoCEdAkKBnCfpUxXV9lChoBkdAcOhleF+NLmgHTRIBaAhHQJCgiF10T111fZQoaAZHQG/d/QrtmcxoB01CAWgIR0CQoRQla8pTdX2UKGgGR0BzBNSzgMtsaAdL82gIR0CQoVt0mtyQdX2UKGgGR0BxTpjAi3XqaAdNDAFoCEdAkKF8gyM1j3V9lChoBkdAbXilqJuVHGgHTSABaAhHQJCiElnh86V1fZQoaAZHQHIjObI91U5oB00kAWgIR0CQojCaZx7zdX2UKGgGR0BG0KOLiuMdaAdL1mgIR0CQowoHs1KodX2UKGgGR0Bwsi0LMLWqaAdNOQFoCEdAkKOX8baRIXV9lChoBkdAcGV4agmJFmgHTRIBaAhHQJCjoT0xubZ1fZQoaAZHQHGYCauwHJNoB00sAWgIR0CQpa3cpLEldX2UKGgGR0BzdJ1A7gbZaAdL6GgIR0CQpjPFvQ4TdX2UKGgGR0BziQ3o9s7/aAdL+2gIR0CQp5ecx0uEdX2UKGgGR0Bxxd8XvYvnaAdNbQFoCEdAkKgmhufmLnV9lChoBkdAbUd1uBMBZWgHTUMBaAhHQJCoSWAwwkB1fZQoaAZHQHBIPttygf5oB00MAWgIR0CQqPC04R29dX2UKGgGR0By672ZiNKiaAdL+WgIR0CQqg56t1ZDdX2UKGgGR0BuXS7btZ3caAdNFQFoCEdAkKpRMN+b3HV9lChoBkdAcApVkc0cfmgHTSQBaAhHQJCqsL+glGB1fZQoaAZHQHII4RmK64FoB00aAWgIR0CQqxQI2OyWdX2UKGgGR0Bsh6PU8V59aAdNVQFoCEdAkKuUOqebu3V9lChoBkdAbKX15jYqXmgHTWsBaAhHQJCr7EyckMV1fZQoaAZHQHKdUlqrR0FoB01UAWgIR0CQrBJgssg/dX2UKGgGR0BxF0KBun/DaAdNNQFoCEdAkK2EoWpIc3V9lChoBkdAbEfEfDDTB2gHTT4BaAhHQJCt1Ng0CRx1fZQoaAZHQHCZZ9qk/KRoB02QAWgIR0CQr+lVLi++dX2UKGgGR0Bs8VCPZIxyaAdNUAFoCEdAkLCoBmwqzHV9lChoBkdAcm70AtFrmGgHTQcBaAhHQJCwvoSteUp1fZQoaAZHQHAhsCDEm6ZoB00dAWgIR0CQsUDRc/t6dX2UKGgGR0Byl8lzEJjUaAdNXwFoCEdAkLGKJ66as3V9lChoBkdAb6LfShJyyWgHTRYBaAhHQJCxq9bor4F1fZQoaAZHQHJzVZowmE5oB0v3aAhHQJCxs1rIo3J1fZQoaAZHQHCn4qwyIpJoB01DAWgIR0CQsc4Z/CqIdX2UKGgGR0BujXVd5Y5laAdL/mgIR0CQsmB7eEZjdX2UKGgGR0BxyCM72criaAdNHQFoCEdAkLLX1FpfyHVlLg=="
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 310,
+    "_n_updates": 248,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
-        ":serialized:": "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",
+        ":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.       ]",
+        "low": "[ -2.5        -2.5       -10.        -10.         -6.2831855 -10.\n  -0.         -0.       ]",
+        "bounded_below": "[ True  True  True  True  True  True  True  True]",
+        "high": "[ 2.5        2.5       10.        10.         6.2831855 10.\n  1.         1.       ]",
+        "bounded_above": "[ True  True  True  True  True  True  True  True]",
+        "low_repr": "[ -2.5        -2.5       -10.        -10.         -6.2831855 -10.\n  -0.         -0.       ]",
+        "high_repr": "[ 2.5        2.5       10.        10.         6.2831855 10.\n  1.         1.       ]",
         "_np_random": null
     },
     "action_space": {
@@ -77,23 +77,39 @@
         "_np_random": null
     },
     "n_envs": 16,
-    "n_steps": 2048,
-    "gamma": 0.99,
-    "gae_lambda": 0.95,
-    "ent_coef": 0.0,
+    "n_steps": 1024,
+    "gamma": 0.999,
+    "gae_lambda": 0.98,
+    "ent_coef": 0.01,
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
+    "rollout_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=",
+        "__module__": "stable_baselines3.common.buffers",
+        "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}",
+        "__doc__": "\n    Rollout buffer used in on-policy algorithms like A2C/PPO.\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to classic advantage when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ",
+        "__init__": "<function RolloutBuffer.__init__ at 0x7fa96303e3e0>",
+        "reset": "<function RolloutBuffer.reset at 0x7fa96303e480>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7fa96303e520>",
+        "add": "<function RolloutBuffer.add at 0x7fa96303e660>",
+        "get": "<function RolloutBuffer.get at 0x7fa96303e700>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x7fa96303e7a0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fa9633e6e80>"
+    },
+    "rollout_buffer_kwargs": {},
     "batch_size": 64,
-    "n_epochs": 10,
+    "n_epochs": 4,
     "clip_range": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":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 sha256:5f241ec98211e478ee9cd6255b9f5c7a14fe3a89c3f822ac1697e8c857ed1eb6
+oid sha256:9f6d08f9317df08a55aed5c0140ae0fec6507954d1f787c002282bf895065483
 size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38296c78e6b638921233ab4751deaf1b6c2853ead9e9f2e8d86b574b070d5527
+oid sha256:7ca14c26711a438074c3e1a39c821500f99fe0a02ba49674c0480b6575a6a762
 size 43762

ppo-LunarLander-v2/system_info.txt

@@ -1,9 +1,8 @@
-- 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: 2.5.1+cu121
+- OS: Linux-5.15.167.4-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Tue Nov 5 00:21:55 UTC 2024
+- Python: 3.12.2
+- Stable-Baselines3: 2.4.0
+- PyTorch: 2.5.1+cu124
 - GPU Enabled: True
 - Numpy: 1.26.4
 - Cloudpickle: 3.1.0
-- Gymnasium: 0.28.1
-- OpenAI Gym: 0.25.2
+- Gymnasium: 1.0.0

results.json

@@ -1 +1 @@
-{"mean_reward": 258.13918, "std_reward": 21.612160663712206, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-05T12:57:21.594695"}
+{"mean_reward": 258.7724123, "std_reward": 15.518107250880249, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-05T16:43:08.843929"}