trained localy

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 288.06 +/- 19.25
+      value: 280.00 +/- 22.33
       name: mean_reward
       verified: false
 ---

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7c3c5a57f0a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c3c5a57f130>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c3c5a57f1c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c3c5a57f250>", "_build": "<function ActorCriticPolicy._build at 0x7c3c5a57f2e0>", "forward": "<function ActorCriticPolicy.forward at 0x7c3c5a57f370>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c3c5a57f400>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c3c5a57f490>", "_predict": "<function ActorCriticPolicy._predict at 0x7c3c5a57f520>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c3c5a57f5b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c3c5a57f640>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c3c5a57f6d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c3c5a58c940>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1730888188719833901, "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": -0.007616000000000067, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 984, "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:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 8, "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:": "gAWVzwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMWi9ob21lL29yZW4vd29yay9sZXdpcy8udmVudi9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4RDAgQBlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMWi9ob21lL29yZW4vd29yay9sZXdpcy8udmVudi9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlGgAjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoH32UfZQoaBaMBGZ1bmOUjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/M6kqMFUyYYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "system_info": {"OS": "Linux-6.9.3-76060903-generic-x86_64-with-glibc2.35 # 202405300957~1726766035~22.04~4092a0e SMP PREEMPT_DYNAMIC Thu S", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.5.1+cu118", "GPU Enabled": "True", "Numpy": "2.1.3", "Cloudpickle": "3.1.0", "Gymnasium": "0.28.1"}}
+{"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 0x7eabc69d2ef0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7eabc69d2f80>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7eabc69d3010>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7eabc69d30a0>", "_build": "<function ActorCriticPolicy._build at 0x7eabc69d3130>", "forward": "<function ActorCriticPolicy.forward at 0x7eabc69d31c0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7eabc69d3250>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7eabc69d32e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7eabc69d3370>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7eabc69d3400>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7eabc69d3490>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7eabc69d3520>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7eabc69cf440>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1730888188719833901, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdgIAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAAIAAAAAAACA7Ca9HzMzPjMAWj5KyrW+hGIQPl3dnT0AAAAAAAAAAM3JzDxiOZg/kliuPU3OIL8ID5c9DpurPQAAAAAAAAAADbvdPVtpDz/D05K9mpgPv3BiGz5dXG29AAAAAAAAAABgATW+/fAVP10JoT4Qmfa+zcOmvOuQID4AAAAAAAAAAAB80DuGarQ/itJXPtB+Qb2BJ4i7koKHvAAAAAAAAAAAzW7DvUjhpbhl4d87ta6fN9bddDtzbJc2AAAAAAAAAACOAoW+53eAP2JqJ77cogS/ZW34vuCjH7wAAAAAAAAAADPYir0pwGu6u4L9uUCL5TRsCDo7koASOQAAgD8AAIA/80eyvUP6CD0Ss4E+gY3Gvim4Kj5zhXS8AAAAAAAAAACNQpK9KdR7uoTphrxSCx+2L7EnuyJxjjUAAAAAAAAAAACs1L02iqA+hitePuKg1b4LLio9TdiePQAAAAAAAAAAAIUWPZ+NmD+AwDg+0M8iv81diT1AAGQ9AAAAAAAAAADNdf+8Co9gu9bLZbyco508hAWoPK1thr0AAIA/AACAPzOs1D0+tYU+W22QvhPl0r5xYHM8tsllvQAAAAAAAAAATWz3PXSZED7KFam+e1S9vj6g07pqjgu+AAAAAAAAAACzQE0+layMPlcaDb/+dqS+SV3lOjffob4AAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLEEsIhpSMAUOUdJRSlC4="}, "_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": -0.007616000000000067, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 984, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 8, "clip_range": {":type:": "<class 'function'>", ":serialized:": "gAWVzwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMWi9ob21lL29yZW4vd29yay9sZXdpcy8udmVudi9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4RDAgQBlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMWi9ob21lL29yZW4vd29yay9sZXdpcy8udmVudi9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlGgAjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoH32UfZQoaBaMBGZ1bmOUjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/yZmZmZmZmoWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "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:": "gAWV/gAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoC4wCaTiUiYiHlFKUKEsDaA9OTk5K/////0r/////SwB0lGKMCl9ucF9yYW5kb22UTnViLg==", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVzwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMWi9ob21lL29yZW4vd29yay9sZXdpcy8udmVudi9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4RDAgQBlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMWi9ob21lL29yZW4vd29yay9sZXdpcy8udmVudi9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlGgAjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoH32UfZQoaBaMBGZ1bmOUjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/M6kqMFUyYYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "weights_only": true, "system_info": {"OS": "Linux-6.9.3-76060903-generic-x86_64-with-glibc2.35 # 202405300957~1726766035~22.04~4092a0e SMP PREEMPT_DYNAMIC Thu S", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.5.1+cu118", "GPU Enabled": "True", "Numpy": "2.1.3", "Cloudpickle": "3.1.0", "Gymnasium": "0.28.1"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d08053a557184969c2114247eb11b5ee78e3c0d36b636d5921d2e27a4c1660c1
-size 147998
+oid sha256:aed6b756d26b40e32006302de3c61cf68e4726b0618377def7e485339251cdb6
+size 148200

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 0x7c3c5a57f0a0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c3c5a57f130>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c3c5a57f1c0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c3c5a57f250>",
-        "_build": "<function ActorCriticPolicy._build at 0x7c3c5a57f2e0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7c3c5a57f370>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c3c5a57f400>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c3c5a57f490>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7c3c5a57f520>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c3c5a57f5b0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c3c5a57f640>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c3c5a57f6d0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7eabc69d2ef0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7eabc69d2f80>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7eabc69d3010>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7eabc69d30a0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7eabc69d3130>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7eabc69d31c0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7eabc69d3250>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7eabc69d32e0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7eabc69d3370>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7eabc69d3400>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7eabc69d3490>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7eabc69d3520>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7c3c5a58c940>"
+        "_abc_impl": "<_abc._abc_data object at 0x7eabc69cf440>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -52,6 +52,21 @@
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
     "_n_updates": 984,
+    "n_steps": 1024,
+    "gamma": 0.999,
+    "gae_lambda": 0.98,
+    "ent_coef": 0.01,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 8,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -69,7 +84,7 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu",
+        ":serialized:": "gAWV/gAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoC4wCaTiUiYiHlFKUKEsDaA9OTk5K/////0r/////SwB0lGKMCl9ucF9yYW5kb22UTnViLg==",
         "n": "4",
         "start": "0",
         "_shape": [],
@@ -77,23 +92,9 @@
         "_np_random": null
     },
     "n_envs": 16,
-    "n_steps": 1024,
-    "gamma": 0.999,
-    "gae_lambda": 0.98,
-    "ent_coef": 0.01,
-    "vf_coef": 0.5,
-    "max_grad_norm": 0.5,
-    "batch_size": 64,
-    "n_epochs": 8,
-    "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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"
-    }
+    },
+    "weights_only": true
 }

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bff37570f8aa409c6a3b12ad46f77c693e09193423d480e5c51e69a129e3f73e
-size 88362
+oid sha256:bafb93767ef2ce28fde10d8ca00659a709e2888a68ecbb6bc4d13c299d929fea
+size 88490

results.json

@@ -1 +1 @@
-{"mean_reward": 288.05967990000005, "std_reward": 19.251605947814177, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-06T14:27:19.536968"}
+{"mean_reward": 279.9956075, "std_reward": 22.333920321322168, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-06T14:52:18.166370"}