Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 176.90 +/- 88.08
+      value: -55.19 +/- 171.48
       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 0x7fd56f497c40>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd56f497ce0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd56f497d80>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd56f497e20>", "_build": "<function ActorCriticPolicy._build at 0x7fd56f497ec0>", "forward": "<function ActorCriticPolicy.forward at 0x7fd56f497f60>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fd56f4a0040>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd56f4a00e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fd56f4a0180>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd56f4a0220>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd56f4a02c0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd56f4a0360>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fd56f49a340>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVaQAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARSZUxVlJOUjAhuZXRfYXJjaJR9lCiMAnBplF2UKEuAS4BLgGWMAnZmlF2UKEuAS4BLgGV1dS4=", "activation_fn": "<class 'torch.nn.modules.activation.ReLU'>", "net_arch": {"pi": [128, 128, 128], "vf": [128, 128, 128]}}, "num_timesteps": 307728, "_total_timesteps": 1500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1776569097575234600, "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:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.803392, "_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": 72, "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:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwFZHR5cGWUjAVudW1weZSMBWR0eXBllJOUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijAFulIwWbnVtcHkuX2NvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlGgLQwgEAAAAAAAAAJSGlFKUjAVzdGFydJRoEWgLQwgAAAAAAAAAAJSGlFKUjAZfc2hhcGWUKYwKX25wX3JhbmRvbZROdWIu", "dtype": "int64", "n": "4", "start": "0", "_shape": [], "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.001, "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 0x7fd56f63c7c0>", "reset": "<function RolloutBuffer.reset at 0x7fd56f63c860>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7fd56f63c900>", "add": "<function RolloutBuffer.add at 0x7fd56f63ca40>", "get": "<function RolloutBuffer.get at 0x7fd56f63cae0>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7fd56f63cb80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fd56f62ad40>"}, "rollout_buffer_kwargs": {}, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>", ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/yZmZmZmZmnNic2Iu", "value_schedule": "ConstantSchedule(val=0.2)"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>", ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/M6kqMFUyYXNic2Iu", "value_schedule": "ConstantSchedule(val=0.0003)"}, "system_info": {"OS": "Linux-5.15.0-139-generic-x86_64-with-glibc2.39 # 149~20.04.1-Ubuntu SMP Wed Apr 16 08:29:56 UTC 2025", "Python": "3.12.3", "Stable-Baselines3": "2.8.0", "PyTorch": "2.11.0+cu130", "GPU Enabled": "False", "Numpy": "2.4.3", "Cloudpickle": "3.1.2", "Gymnasium": "1.2.3", "OpenAI Gym": "0.26.2"}}
+{"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 0x7fa7c551f1a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa7c551f240>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa7c551f2e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa7c551f380>", "_build": "<function ActorCriticPolicy._build at 0x7fa7c551f420>", "forward": "<function ActorCriticPolicy.forward at 0x7fa7c551f4c0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fa7c551f560>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa7c551f600>", "_predict": "<function ActorCriticPolicy._predict at 0x7fa7c551f6a0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa7c551f740>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa7c551f7e0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa7c551f880>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fa7c5520d40>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "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", "features_extractor_class": "<class '__main__.DenseResidualExtractor'>", "features_extractor_kwargs": {"features_dim": 64, "num_layers": 3}, "activation_fn": "<class 'torch.nn.modules.activation.ReLU'>", "net_arch": {"pi": [64], "vf": [64]}}, "num_timesteps": 414272, "_total_timesteps": 1500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1776572260190232744, "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:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.7269333333333333, "_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": 100, "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:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwFZHR5cGWUjAVudW1weZSMBWR0eXBllJOUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijAFulIwWbnVtcHkuX2NvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlGgLQwgEAAAAAAAAAJSGlFKUjAVzdGFydJRoEWgLQwgAAAAAAAAAAJSGlFKUjAZfc2hhcGWUKYwKX25wX3JhbmRvbZROdWIu", "dtype": "int64", "n": "4", "start": "0", "_shape": [], "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.001, "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 0x7fa7c59afce0>", "reset": "<function RolloutBuffer.reset at 0x7fa7c59afd80>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7fa7c59afe20>", "add": "<function RolloutBuffer.add at 0x7fa7c59aff60>", "get": "<function RolloutBuffer.get at 0x7fa7c59cc040>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7fa7c59cc0e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fa7c597ac40>"}, "rollout_buffer_kwargs": {}, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>", ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/yZmZmZmZmnNic2Iu", "value_schedule": "ConstantSchedule(val=0.2)"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>", ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/M6kqMFUyYXNic2Iu", "value_schedule": "ConstantSchedule(val=0.0003)"}, "system_info": {"OS": "Linux-5.15.0-139-generic-x86_64-with-glibc2.39 # 149~20.04.1-Ubuntu SMP Wed Apr 16 08:29:56 UTC 2025", "Python": "3.12.3", "Stable-Baselines3": "2.8.0", "PyTorch": "2.11.0+cu130", "GPU Enabled": "False", "Numpy": "2.4.3", "Cloudpickle": "3.1.2", "Gymnasium": "1.2.3", "OpenAI Gym": "0.26.2"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4fc0883f8a0e470449b266f2a036b713e9c03d75cdc1d795f71ce5b3510670f
-size 864889
+oid sha256:c781ee4a1dc325cf85a0697f669d89df5f49ae739eb7ab4ecddd482ff30f6960
+size 304501

ppo-LunarLander-v2/data

@@ -4,50 +4,51 @@
         ":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 0x7fd56f497c40>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fd56f497ce0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fd56f497d80>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fd56f497e20>",
-        "_build": "<function ActorCriticPolicy._build at 0x7fd56f497ec0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7fd56f497f60>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fd56f4a0040>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fd56f4a00e0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7fd56f4a0180>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fd56f4a0220>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fd56f4a02c0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fd56f4a0360>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7fa7c551f1a0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fa7c551f240>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fa7c551f2e0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fa7c551f380>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fa7c551f420>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fa7c551f4c0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fa7c551f560>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fa7c551f600>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fa7c551f6a0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fa7c551f740>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fa7c551f7e0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fa7c551f880>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7fd56f49a340>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fa7c5520d40>"
     },
     "verbose": 1,
     "policy_kwargs": {
         ":type:": "<class 'dict'>",
-        ":serialized:": "gAWVaQAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARSZUxVlJOUjAhuZXRfYXJjaJR9lCiMAnBplF2UKEuAS4BLgGWMAnZmlF2UKEuAS4BLgGV1dS4=",
+        ":serialized:": "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",
+        "features_extractor_class": "<class '__main__.DenseResidualExtractor'>",
+        "features_extractor_kwargs": {
+            "features_dim": 64,
+            "num_layers": 3
+        },
         "activation_fn": "<class 'torch.nn.modules.activation.ReLU'>",
         "net_arch": {
             "pi": [
-                128,
-                128,
-                128
+                64
             ],
             "vf": [
-                128,
-                128,
-                128
+                64
             ]
         }
     },
-    "num_timesteps": 307728,
+    "num_timesteps": 414272,
     "_total_timesteps": 1500000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1776569097575234600,
+    "start_time": 1776572260190232744,
     "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'>",
@@ -57,17 +58,17 @@
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": 0.803392,
+    "_current_progress_remaining": 0.7269333333333333,
     "_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": 72,
+    "_n_updates": 100,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -105,14 +106,14 @@
         "__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 0x7fd56f63c7c0>",
-        "reset": "<function RolloutBuffer.reset at 0x7fd56f63c860>",
-        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7fd56f63c900>",
-        "add": "<function RolloutBuffer.add at 0x7fd56f63ca40>",
-        "get": "<function RolloutBuffer.get at 0x7fd56f63cae0>",
-        "_get_samples": "<function RolloutBuffer._get_samples at 0x7fd56f63cb80>",
+        "__init__": "<function RolloutBuffer.__init__ at 0x7fa7c59afce0>",
+        "reset": "<function RolloutBuffer.reset at 0x7fa7c59afd80>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7fa7c59afe20>",
+        "add": "<function RolloutBuffer.add at 0x7fa7c59aff60>",
+        "get": "<function RolloutBuffer.get at 0x7fa7c59cc040>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x7fa7c59cc0e0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7fd56f62ad40>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fa7c597ac40>"
     },
     "rollout_buffer_kwargs": {},
     "batch_size": 64,

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f13aa5df91e2b37521a92cdf8951f6700abcad8bccdb9e22331cb07c163dd24
-size 565139
+oid sha256:e22e71ae0f3468dc9b6e949ce7dac0408298f71ec20f06bd2c52e95852fe6112
+size 186771

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68104dbd52ceef87e3c453a1bc1f05a6ca4bed393cf7bbd4f5b045d3e74be678
-size 282035
+oid sha256:aa5937c4ff32ea68a45307c54b88c63baac8ab2c2e31797adae35598e009ed70
+size 96243

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f40081aaf0baf90e2f786a2985264c0ee5109adc1d2b85a1876eeaaa1d2814c9
-size 151089
+oid sha256:73ddf93a8c56f16b3f6091d89ec23890b9c8551290456e44c39d1767fbff9bac
+size 157362

results.json

@@ -1 +1 @@
-{"mean_reward": 176.89851710396957, "std_reward": 88.08224815178541, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-19T03:40:33.458880"}
+{"mean_reward": -55.19425365372153, "std_reward": 171.47774956615166, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-19T04:34:10.778045"}