Upload PPO LunarLander-v2 trained agent v2

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 272.00 +/- 18.85
+      value: 135.53 +/- 64.85
       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 0x71f51563a700>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x71f51563a7a0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x71f51563a840>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x71f51563a8e0>", "_build": "<function ActorCriticPolicy._build at 0x71f51563a980>", "forward": "<function ActorCriticPolicy.forward at 0x71f51563aa20>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x71f51563aac0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x71f51563ab60>", "_predict": "<function ActorCriticPolicy._predict at 0x71f51563ac00>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x71f51563aca0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x71f51563ad40>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x71f51563ade0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x71f515a73a40>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 5013504, "_total_timesteps": 5000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1712587798767685425, "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:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAABAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0027007999999999477, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWV5wsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHHb1RHf/FSMAWyUS+OMAXSUR0CUw+ywwCbMdX2UKGgGR0BzrueCkGiYaAdLxWgIR0CUxA8v24/edX2UKGgGR0Bzixx82JizaAdNCAFoCEdAlMQjwUg0THV9lChoBkdAcdZXrt3OfWgHS/BoCEdAlMRHarWAgHV9lChoBkdAcaA43m3fAWgHTQUBaAhHQJTEc65oXbd1fZQoaAZHQHEPV2JSBLBoB0vXaAhHQJTEgRh+fAd1fZQoaAZHQHMfra7EpAloB0vtaAhHQJTElLOAy2x1fZQoaAZHQHFDRvm5lOJoB0vfaAhHQJTE0Nd7fHh1fZQoaAZHQHPDm6wt8NRoB0vtaAhHQJTE493bEgp1fZQoaAZHQHFC8xO+IuZoB0vqaAhHQJTFB5VwPy11fZQoaAZHQHCtoXwb2lFoB0vmaAhHQJTFHksBhhJ1fZQoaAZHQHEqAPZqVQhoB00GAWgIR0CUxR3FUADJdX2UKGgGR0BxGPIOpbUxaAdL8GgIR0CUxSrnkkrxdX2UKGgGR0BxvCPZIxxlaAdL3GgIR0CUxSg7YChfdX2UKGgGR0Bx4EbVBlcyaAdL62gIR0CUxW86mwaBdX2UKGgGR0BxXApYs/Y8aAdL6GgIR0CUxX43m3fAdX2UKGgGR0BymhKAavRraAdLyGgIR0CUxcmVJL/TdX2UKGgGR0BuccwWWQfZaAdL5GgIR0CUxduIhyKfdX2UKGgGR0Bxb5PKuB+XaAdNCwFoCEdAlMXuSr5qM3V9lChoBkdAcjL8fms/6mgHS/toCEdAlMXzTa0x/XV9lChoBkdAcG+1HOKO1mgHS+xoCEdAlMY8jeKsMnV9lChoBkdAcgIHCoCMgmgHS99oCEdAlMZEyULUkXV9lChoBkdAcFjVE/jbSWgHS/VoCEdAlMZcRcu8LHV9lChoBkdAcvQBVMmF8GgHS8poCEdAlMapaNdZ73V9lChoBkdAcQ59RJmNBGgHS+hoCEdAlMaup4rz5HV9lChoBkdAbsTScbzbvmgHS/poCEdAlMbAk5ZKWnV9lChoBkdAcyT1cdHUdGgHS8xoCEdAlMa7vb48EHV9lChoBkdAb39m+TNdJWgHS9hoCEdAlMbIgzP8h3V9lChoBkdAbbGyVv/BFmgHS+BoCEdAlMbidvsJIHV9lChoBkdAczs+/gzguWgHS/RoCEdAlMbmqYJE6XV9lChoBkdAcpZlAu7HyWgHS/BoCEdAlMqvrGBFu3V9lChoBkdAcQb9+w1R+GgHS/poCEdAlMrTaPCEYnV9lChoBkdAcDUQTVUdaWgHS9VoCEdAlMrnztkWh3V9lChoBkdAck0fXf642GgHS+NoCEdAlMryKR+z+nV9lChoBkdAcGMA/9pAU2gHS+9oCEdAlMs1/H5rQHV9lChoBkdAckKe18b70mgHS/toCEdAlMtJXdTHbXV9lChoBkdAb6LIVdonKGgHS9ZoCEdAlMtPk/8l5XV9lChoBkdAcn8AmzByj2gHS89oCEdAlMte1ndwenV9lChoBkdAcfs5Lh73PGgHS+5oCEdAlMuBkiD/VHV9lChoBkdAdByIp6QeWGgHS8doCEdAlMumJN0vG3V9lChoBkdAcjB6VdHDrWgHS95oCEdAlMvaaLGaQXV9lChoBkdAct1zEJjUeGgHS+loCEdAlMvYgA6uGXV9lChoBkdAcx7T987ZF2gHS/5oCEdAlMv+3H7xeHV9lChoBkdAcG8uDjBEa2gHS/NoCEdAlMv3gccU/XV9lChoBkdAcU3QDmr8zmgHS+FoCEdAlMwCfL9uP3V9lChoBkdAc2DH0btJF2gHTQMBaAhHQJTMOvaDf3x1fZQoaAZHQHJ6tytFKChoB0vOaAhHQJTMPSWqtHR1fZQoaAZHQHJNQG0NSZVoB0vMaAhHQJTMWmvW6LB1fZQoaAZHQHFit+G47RxoB0vgaAhHQJTMliUgSvl1fZQoaAZHQHDZdwWFev9oB0voaAhHQJTMsWj45951fZQoaAZHQHGVtN8E3bVoB0vWaAhHQJTM5T0g8r91fZQoaAZHQHMOAyM1jy5oB0vNaAhHQJTM62sq8UV1fZQoaAZHQHIvBhhH9WJoB0voaAhHQJTNEMMI/qx1fZQoaAZHQHOGGYKIBR1oB0vyaAhHQJTNDDej2zx1fZQoaAZHQHBfqlk6LfloB0vtaAhHQJTNUHqu8sd1fZQoaAZHQHOfcjqv/zdoB0vTaAhHQJTNe1F6Rhd1fZQoaAZHQHK1vhddE9doB0vDaAhHQJTNhOrQw9J1fZQoaAZHQHF+XoPkJa9oB0v2aAhHQJTNjQswtap1fZQoaAZHQG8siwr1/UhoB0vgaAhHQJTNk9s7+1l1fZQoaAZHQHOkG9g4OtpoB0u+aAhHQJTNuW+oLoh1fZQoaAZHQHHsuP/7zkJoB0vjaAhHQJTNtpqREF51fZQoaAZHQHDZ4r8R+SdoB0v1aAhHQJTN3ztkWh11fZQoaAZHQHIOHDm8ujBoB0vgaAhHQJTN9VzZHut1fZQoaAZHQHGYV14gRsdoB0vXaAhHQJTOAry1/lR1fZQoaAZHQHGUTw2ETQFoB0vWaAhHQJTOM8zQ/ot1fZQoaAZHQHGVdDIBBAxoB0viaAhHQJTOYgHNX5p1fZQoaAZHQHAIfCuU2UBoB0vSaAhHQJTOcbtJFsp1fZQoaAZHQG8IsWweNkxoB0vvaAhHQJTOrXpW3jN1fZQoaAZHQHNqSVbA1vVoB0vkaAhHQJTOvEcbR4R1fZQoaAZHQHELl9Brvb5oB0v+aAhHQJTO7VoYekp1fZQoaAZHQHMYxKxs2vVoB0voaAhHQJTPCJbdJrd1fZQoaAZHQHA1L5/LDAJoB0vMaAhHQJTPCkCV8kV1fZQoaAZHQG/y7XpW3jNoB0vuaAhHQJTPOyzHCGh1fZQoaAZHQHDa7zkIX0poB0vdaAhHQJTPWTKT0QN1fZQoaAZHQHOWRFNL129oB0vdaAhHQJTPVnIyTIN1fZQoaAZHQHIccma6ST1oB0v/aAhHQJTPZQcghbJ1fZQoaAZHQHKmtgBtDUpoB0v6aAhHQJTPaQo1DSh1fZQoaAZHQG7hX2EkB0ZoB0vdaAhHQJTPfYNAkcF1fZQoaAZHQHLhvQrtmcxoB0vxaAhHQJTPshJRO1x1fZQoaAZHQHKISKBNEgJoB0vvaAhHQJTPvA9FF2F1fZQoaAZHQHCO4VdonKJoB0vXaAhHQJTP8nqmj0t1fZQoaAZHQHJYyyprDZVoB0v2aAhHQJTP/boKUml1fZQoaAZHQHJddvGZNPBoB0vLaAhHQJTQJy7wrlN1fZQoaAZHQG3Kw176YVtoB0vbaAhHQJTQVDNQj2V1fZQoaAZHQHE+0WdmQKdoB00FAWgIR0CU0FoKlYU4dX2UKGgGR0Bx39lK9PDYaAdLymgIR0CU0HrTH80ldX2UKGgGR0ByijabnX/YaAdLymgIR0CU0Hw9JSR9dX2UKGgGR0BxX57mdRR/aAdL4WgIR0CU0IxqfvnbdX2UKGgGR0Bxi+0b961LaAdLzWgIR0CU0Mtk4FRpdX2UKGgGR0BwnhkH2RJVaAdL0mgIR0CU0NhttQ9BdX2UKGgGR0By2vjT8YQ8aAdL9WgIR0CU0P9AX2ugdX2UKGgGR0BzSl7BwdbQaAdL6GgIR0CU0RUdaMaTdX2UKGgGR0BzqKTFERapaAdLxmgIR0CU0SlVcUuddX2UKGgGR0BwFdSqEOAiaAdL72gIR0CU0TnRb8m8dX2UKGgGR0BwaM0vXbudaAdL/GgIR0CU0TfMfRu1dX2UKGgGR0ByuVYFJQLvaAdL12gIR0CU0YfqHGjsdX2UKGgGR0By7OoXKr7waAdL/mgIR0CU0ZiyIHkcdX2UKGgGR0Bx64xi5NGmaAdLzWgIR0CU0d0UXYUWdX2UKGgGR0BxFDXe3x4IaAdL7WgIR0CU0fDVH4GmdX2UKGgGR0Bxvjv9cbBHaAdNBgFoCEdAlNH2fGuLaXVlLg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1224, "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": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]", "high": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]", "low_repr": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]", "high_repr": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 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": 0.0001, "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 0x71f5155cb2e0>", "reset": "<function RolloutBuffer.reset at 0x71f5155cb380>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x71f5155cb420>", "add": "<function RolloutBuffer.add at 0x71f5155cb560>", "get": "<function RolloutBuffer.get at 0x71f5155cb600>", "_get_samples": "<function RolloutBuffer._get_samples at 0x71f5155cb6a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x71f5155c50c0>"}, "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:": "gAWVfgIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwiVAZcAiQFTAJROhZQpjAFflIWUjFovaG9tZS9tbC9taW5pZm9yZ2UzL2VudnMvSEYvbGliL3B5dGhvbjMuMTIvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5RLg0MI+IAA2A8SiAqUQwCUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flGgMdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpRoAIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCB9lH2UKGgYaA2MDF9fcXVhbG5hbWVfX5RoDowPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoGYwHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/M6kqMFUyYYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "system_info": {"OS": "Linux-6.5.0-26-generic-x86_64-with-glibc2.35 # 26~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Mar 12 10:22:43 UTC 2", "Python": "3.12.2", "Stable-Baselines3": "2.3.0", "PyTorch": "2.1.2.post3", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1"}}
+{"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 0x785ae0132700>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x785ae01327a0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x785ae0132840>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x785ae01328e0>", "_build": "<function ActorCriticPolicy._build at 0x785ae0132980>", "forward": "<function ActorCriticPolicy.forward at 0x785ae0132a20>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x785ae0132ac0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x785ae0132b60>", "_predict": "<function ActorCriticPolicy._predict at 0x785ae0132c00>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x785ae0132ca0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x785ae0132d40>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x785ae0132de0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x785ae0138940>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 5013504, "_total_timesteps": 5000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1712591841754758090, "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": -0.0027007999999999477, "_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": 1224, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVZgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAADAvwAAwL8AAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAwD8AAMA/AACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFNbLTEuNSAgICAgICAtMS41ICAgICAgIC01LiAgICAgICAgLTUuICAgICAgICAtMy4xNDE1OTI3IC01LgogLTAuICAgICAgICAtMC4gICAgICAgXZSMCWhpZ2hfcmVwcpSMS1sxLjUgICAgICAgMS41ICAgICAgIDUuICAgICAgICA1LiAgICAgICAgMy4xNDE1OTI3IDUuICAgICAgICAxLgogMS4gICAgICAgXZSMCl9ucF9yYW5kb22UTnViLg==", "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": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]", "high": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]", "low_repr": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]", "high_repr": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 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": 0.99999, "gae_lambda": 0.98, "ent_coef": 0.1, "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 0x785ae00bf2e0>", "reset": "<function RolloutBuffer.reset at 0x785ae00bf380>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x785ae00bf420>", "add": "<function RolloutBuffer.add at 0x785ae00bf560>", "get": "<function RolloutBuffer.get at 0x785ae00bf600>", "_get_samples": "<function RolloutBuffer._get_samples at 0x785ae00bf6a0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x785ae00c4140>"}, "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-6.5.0-26-generic-x86_64-with-glibc2.35 # 26~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Mar 12 10:22:43 UTC 2", "Python": "3.12.2", "Stable-Baselines3": "2.3.0", "PyTorch": "2.1.2.post3", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d117ab6ed13ec42e1e4276080552e30064a93661806030c061288e3edb2825f7
-size 149484
+oid sha256:abb2abc7210deb84a6db4b530910214c86145f011531f1b78fe0056d5cc35a4b
+size 149475

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 0x71f51563a700>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x71f51563a7a0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x71f51563a840>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x71f51563a8e0>",
-        "_build": "<function ActorCriticPolicy._build at 0x71f51563a980>",
-        "forward": "<function ActorCriticPolicy.forward at 0x71f51563aa20>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x71f51563aac0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x71f51563ab60>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x71f51563ac00>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x71f51563aca0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x71f51563ad40>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x71f51563ade0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x785ae0132700>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x785ae01327a0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x785ae0132840>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x785ae01328e0>",
+        "_build": "<function ActorCriticPolicy._build at 0x785ae0132980>",
+        "forward": "<function ActorCriticPolicy.forward at 0x785ae0132a20>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x785ae0132ac0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x785ae0132b60>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x785ae0132c00>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x785ae0132ca0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x785ae0132d40>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x785ae0132de0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x71f515a73a40>"
+        "_abc_impl": "<_abc._abc_data object at 0x785ae0138940>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -26,16 +26,16 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1712587798767685425,
+    "start_time": 1712591841754758090,
     "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'>",
-        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAABAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
     },
     "_last_original_obs": null,
     "_episode_num": 0,
@@ -45,7 +45,7 @@
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "gAWV4QsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQEBYZflZHNKMAWyUS0+MAXSUR0CQWiLnLaEjdX2UKGgGR0AqM/r0J4SpaAdLcmgIR0CQWi3ueBhAdX2UKGgGR0AzcF36hxo7aAdLWGgIR0CQWjAn2IwedX2UKGgGR0BJtOb7TDwZaAdLUmgIR0CQWjBClabGdX2UKGgGR0BE19z4k/r0aAdLd2gIR0CQWjjFyaNNdX2UKGgGR0BRmpRsMy8BaAdLm2gIR0CQWlPzWf9QdX2UKGgGR0BQHi3b212JaAdLcWgIR0CQWmbxEv0zdX2UKGgGR0A4zMPjGT9saAdLYGgIR0CQWmp0OmSAdX2UKGgGR0A5EupS75EdaAdLZ2gIR0CQWoeIEbHZdX2UKGgGR0ApLGXHBDXwaAdLb2gIR0CQWpIwdsBRdX2UKGgGR0A+0UjLSuyNaAdLlmgIR0CQWre54GD+dX2UKGgGR0BmTUTlDF6zaAdN6ANoCEdAkFrGRigCfnV9lChoBkdAMcB1DBuXNWgHS2FoCEdAkFrRnJ1aGHV9lChoBkfAIwpVsDW9UWgHS4FoCEdAkFrTeGfwqnV9lChoBkdAT/Uhs67ulWgHS1ZoCEdAkFrTcuanaXV9lChoBkdAJoKVpsXSB2gHS1toCEdAkFrTGcWj5HV9lChoBkdAMMw3T/hl2GgHS3BoCEdAkFrS/wiJO3V9lChoBkdASPc6PsAvMGgHS3VoCEdAkFrhew9q13V9lChoBkdAOaQDvE0iyWgHS3loCEdAkFr5TqB3A3V9lChoBkdARPxf2K2rn2gHS11oCEdAkFr/IsAeaXV9lChoBkdAOpMxGlQ/HGgHS05oCEdAkFsLpFCswXV9lChoBkdAT1h+fAbhnGgHS4poCEdAkFsPGZNO/XV9lChoBkdANgFK02LpA2gHS2toCEdAkFsUkjX4CnV9lChoBkc/xUpd8iOea2gHS15oCEdAkFsZ1V5rxnV9lChoBkdARB9R3u/lAGgHS1toCEdAkFs3w5NoJ3V9lChoBkdARNWtwJgLJGgHS11oCEdAkFtEw8GLUHV9lChoBkdASbMXenAIp2gHS1doCEdAkFtHktEofHV9lChoBkdAUDtZGKAJ9mgHS55oCEdAkFtJEUj9oHV9lChoBkdANcMx46fapWgHS1loCEdAkFtZh8Yyf3V9lChoBkdARm2O+7Dl5mgHS3VoCEdAkFtxf4REnnV9lChoBkdARikfDDTBqWgHS3poCEdAkFt46bONYXV9lChoBkdAUK1xhlUZN2gHS3toCEdAkFt5Ec81XXV9lChoBkdAIVPRZ2ZAp2gHS4FoCEdAkFuCed07sHV9lChoBkdAQ+6/ub7TD2gHS2toCEdAkFurOmixmnV9lChoBkdARGnYcvM8o2gHS1NoCEdAkFuu4wyqMnV9lChoBkdATkhM+NcW02gHS1ZoCEdAkFvGhqTKT3V9lChoBkdAS2oCwKSgXmgHS5FoCEdAkFvIgvDgqHV9lChoBkdAOBdmQKa5PWgHS4poCEdAkFvSbH6uXHV9lChoBkdARguGucMEzWgHS4JoCEdAkFvV7tzCDXV9lChoBkdAUnE4rBj4H2gHS4loCEdAkFvVIAfdRHV9lChoBkc/9SgGr0aqCGgHS1poCEdAkFvgEyLyc3V9lChoBkdAVAqARTS9d2gHS59oCEdAkFvkEcKgI3V9lChoBkdARm1YfW+XaGgHS3doCEdAkFvyqp97W3V9lChoBkdAOcLgwXZXdWgHS1BoCEdAkFv5M+NcW3V9lChoBkdAQMz4etCAtmgHS31oCEdAkFv9ygf2b3V9lChoBkdASro+QlruY2gHS2JoCEdAkFwCwnpjc3V9lChoBkdATw8Nz8xbjmgHS2NoCEdAkFwKkdmxuHV9lChoBkdAQCI46wMYuWgHS1NoCEdAkFwollbu+nV9lChoBkdAPWzJEH+qBGgHS4FoCEdAkFw3Ns3yZ3V9lChoBkdAUIagam4y5GgHS01oCEdAkFxCfUWl/HV9lChoBkdAIRnXd0q6OGgHS2doCEdAkFxFK9PDYXV9lChoBkdAROe01IiC8WgHS1loCEdAkFxJzPrv9nV9lChoBkdARSbBl+Vkc2gHS1JoCEdAkFxN65XlsHV9lChoBkdAQrcglnh86WgHS1BoCEdAkFxVBIFvAHV9lChoBkdAPubvw3HaOGgHS3hoCEdAkFx6ekHlfnV9lChoBkfAEeteUpuuR2gHS21oCEdAkFyGEoOQQ3V9lChoBkdARSW+bmU4aWgHS3toCEdAkFyMPBi1A3V9lChoBkdAHQ7cO9WZJGgHS2doCEdAkFyOWBz3iHV9lChoBkdAQEfc580DU2gHS2NoCEdAkFyZqynk1nV9lChoBkdAOmlGgBcRlGgHS25oCEdAkFygX668QXV9lChoBkdAQxZpBX0Xg2gHS21oCEdAkFyj5ftx/HV9lChoBkdAM4VGXokiU2gHS1RoCEdAkFyrkGRmsnV9lChoBkfAGD9qUNayKWgHS1loCEdAkFzAK0D2anV9lChoBkdARaGevpyIYWgHS19oCEdAkFzULYwqRXV9lChoBkdASRkTL4etCGgHS4doCEdAkFzZAY51eXV9lChoBkdARXcJUo8ZDWgHS2poCEdAkFzn5nDiwXV9lChoBkdAQYMZgogFHWgHS2xoCEdAkFz7u2JBPnV9lChoBkdAGzIfKZDzAmgHS1poCEdAkF0GjCYTkHV9lChoBkdAR/B6By0a62gHS4NoCEdAkF0Zg1FYuHV9lChoBkdATHg9C/oJRmgHS0toCEdAkF0Y4EOiFnV9lChoBkdAKp9adMCcPWgHS11oCEdAkF0rQC0WuXV9lChoBkdAQU8RUWEbpGgHS15oCEdAkF00b5uZTnV9lChoBkdASxH/WDpTuWgHS51oCEdAkF1ANkOI7HV9lChoBkdASZq/47A+IWgHS3ZoCEdAkF1Gq5sj3XV9lChoBkdARMkOVgQYk2gHS39oCEdAkF1XJPqLTHV9lChoBkdARpGo3rD632gHS1loCEdAkF1paiblR3V9lChoBkdAOhQhW5paimgHS3RoCEdAkF18QI2OyXV9lChoBkdAPAtIf8uSOmgHS49oCEdAkF2TUAksz3V9lChoBkdAMR1UVBUrCmgHS11oCEdAkF2XY6GQCHV9lChoBkdAUfYppeu3dGgHS35oCEdAkF2ly7wrlXV9lChoBkdAOVizcAR02mgHS3ZoCEdAkF2uZXuE3HV9lChoBkdAQFcdxQzk62gHS1xoCEdAkF21nqVyFXV9lChoBkdAMEeZ5Rjz7WgHS3FoCEdAkF3HW8RL9XV9lChoBkdAPIhIvrWy1WgHS3BoCEdAkF3Zqh11XHV9lChoBkdAQwsZP2wmmmgHS2doCEdAkF30Iw/PgXV9lChoBkdAFOnEl3QlbGgHS2JoCEdAkF4FxOtW/HV9lChoBkdAJfTfaYeDF2gHS2xoCEdAkF4FkhA4XHV9lChoBkdATey3Zwn6VWgHS4FoCEdAkF4N74SHunV9lChoBkdAREx19v0h/2gHS19oCEdAkF4VD4QBgnV9lChoBkdASo21pj+aSmgHS4doCEdAkF4i8WbgCXV9lChoBkdAP/EHlfZ26mgHS19oCEdAkF4o2fkFOnV9lChoBkdAQMFDv3JxN2gHS3poCEdAkF54yj59E3V9lChoBkdAQsC9du5z52gHS35oCEdAkF59IXj2jHV9lChoBkdAKkCBf8dgfGgHS3VoCEdAkF5/dl/YrnV9lChoBkdAErCPZIxxk2gHS1RoCEdAkF6VGgBcRnV9lChoBkdARGajUNKAa2gHS39oCEdAkF6dnCfpU3V9lChoBkdAJ3EvsZ5zHWgHS2loCEdAkF6iSNfgJnV9lChoBkdASo19H+ZPVWgHS3ZoCEdAkF6nqu8sc3V9lChoBkdAR0fVf/m1Y2gHS4JoCEdAkF6rfpD/l3V9lChoBkdAToSon8baRWgHS11oCEdAkF64Yzi0fHVlLg=="
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
@@ -78,9 +78,9 @@
     },
     "n_envs": 16,
     "n_steps": 1024,
-    "gamma": 0.999,
+    "gamma": 0.99999,
     "gae_lambda": 0.98,
-    "ent_coef": 0.0001,
+    "ent_coef": 0.1,
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
     "rollout_buffer_class": {
@@ -89,14 +89,14 @@
         "__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 0x71f5155cb2e0>",
-        "reset": "<function RolloutBuffer.reset at 0x71f5155cb380>",
-        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x71f5155cb420>",
-        "add": "<function RolloutBuffer.add at 0x71f5155cb560>",
-        "get": "<function RolloutBuffer.get at 0x71f5155cb600>",
-        "_get_samples": "<function RolloutBuffer._get_samples at 0x71f5155cb6a0>",
+        "__init__": "<function RolloutBuffer.__init__ at 0x785ae00bf2e0>",
+        "reset": "<function RolloutBuffer.reset at 0x785ae00bf380>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x785ae00bf420>",
+        "add": "<function RolloutBuffer.add at 0x785ae00bf560>",
+        "get": "<function RolloutBuffer.get at 0x785ae00bf600>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x785ae00bf6a0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x71f5155c50c0>"
+        "_abc_impl": "<_abc._abc_data object at 0x785ae00c4140>"
     },
     "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:a40f5babda1d4b5f2277f67ae116f772ea6d1b178ddf1ec5b7578c43fe38fe9c
+oid sha256:23f7eee24e1a669c07418eb85887dbed0979072a42360ec712fb964145b63e7c
 size 87978

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0bb921fa05df01a82b16cc8f392d761d86e1d9e8a6a86aa763aa32c6c993ddf
+oid sha256:3106342d9dbabb78e417bca8b7f0b3c01ba85531e5be187d0db3ee0b54c81c65
 size 43634

results.json

@@ -1 +1 @@
-{"mean_reward": 271.9985474577791, "std_reward": 18.8487721508229, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-08T17:12:12.906580"}
+{"mean_reward": 135.52522942874623, "std_reward": 64.84720515687077, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-08T18:14:54.120491"}