Uploading PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 288.18 +/- 22.72
+      value: 286.42 +/- 14.55
       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 0x7df22a5cb880>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7df22a5cb910>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7df22a5cb9a0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7df22a5cba30>", "_build": "<function ActorCriticPolicy._build at 0x7df22a5cbac0>", "forward": "<function ActorCriticPolicy.forward at 0x7df22a5cbb50>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7df22a5cbbe0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7df22a5cbc70>", "_predict": "<function ActorCriticPolicy._predict at 0x7df22a5cbd00>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7df22a5cbd90>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7df22a5cbe20>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7df22a5cbeb0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7df22a5bba00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2015232, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1702395723739403922, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAIDIYz3u4ac/m6SpPSYVJ7/RtLA8XstTPgAAAAAAAAAArZolPvDdhD4bgIm+e5QDv1EsyD3wABC+AAAAAAAAAABNMyq9Bcmwu94rfDtiDyI9K8ObvPAPXz0AAIA/AACAP5prLL0fVbq5xUn5vfNiBLNMHYC74EflMgAAgD8AAAAAAFDVOikOKT2D/mG+zM4wvvl0ub2SOn+9AAAAAAAAAAAz1zi9goT/Pitm5DsJTy2/duG2vVOChjsAAAAAAAAAAK15Zz6Y2AA/xiYIvUBdKr8aB4w+cK/9vQAAAAAAAAAAzYXmPPbMCbpK06y6vDOUNNi4ZLsh9so5AACAPwAAgD/NvpU8BcDXuy/RiT3uU249Tn48vQC+2boAAIA/AACAPwCP87z2lDi68tRKPeV0H7ad8v04zYwatQAAgD8AAIA/APzbu65xvbqfebm2C1StsTM5qDmy1dU1AACAPwAAgD9tPQo+ogOcP3JDfj6H1D6/KlUOPv2TTj4AAAAAAAAAAAC45Tyuj5O6qq4Ts7P7QjFaKgc7aiGzMwAAgD8AAIA/M6OeOo8OfbrKFko2DwNIMfGJ4LnDdnG1AACAPwAAgD/NFMK7j+ZuutXfRzpe0281iQaQOi0SZrkAAIA/AACAP8Dmhz0fe/I6DtbKvW5uAjwG/1S83ngquwAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="}, "_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": -0.007616000000000067, "_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": 2460, "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "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": 20, "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-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ", "__init__": "<function ActorCriticPolicy.__init__ at 0x795978f3c3a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x795978f3c430>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x795978f3c4c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x795978f3c550>", "_build": "<function ActorCriticPolicy._build at 0x795978f3c5e0>", "forward": "<function ActorCriticPolicy.forward at 0x795978f3c670>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x795978f3c700>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x795978f3c790>", "_predict": "<function ActorCriticPolicy._predict at 0x795978f3c820>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x795978f3c8b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x795978f3c940>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x795978f3c9d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7959798ca540>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 16384, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1702494474649272749, "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": 0.983616, "_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": 597, "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "system_info": {"OS": "Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:902b423534bbd5e95e02c0db8697cb6038a723574e8a85845601f818b038c6d2
-size 147928
+oid sha256:4e4d85dc92a418c89531bf225dacc0e1a24e23687f90c0cce8ce0ed2a18b80aa
+size 146569

ppo-LunarLander-v2/data

@@ -4,34 +4,34 @@
         ":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 0x7df22a5cb880>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7df22a5cb910>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7df22a5cb9a0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7df22a5cba30>",
-        "_build": "<function ActorCriticPolicy._build at 0x7df22a5cbac0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7df22a5cbb50>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7df22a5cbbe0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7df22a5cbc70>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7df22a5cbd00>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7df22a5cbd90>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7df22a5cbe20>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7df22a5cbeb0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x795978f3c3a0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x795978f3c430>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x795978f3c4c0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x795978f3c550>",
+        "_build": "<function ActorCriticPolicy._build at 0x795978f3c5e0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x795978f3c670>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x795978f3c700>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x795978f3c790>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x795978f3c820>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x795978f3c8b0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x795978f3c940>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x795978f3c9d0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7df22a5bba00>"
+        "_abc_impl": "<_abc._abc_data object at 0x7959798ca540>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 2015232,
-    "_total_timesteps": 2000000,
+    "num_timesteps": 16384,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1702395723739403922,
+    "start_time": 1702494474649272749,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAIDIYz3u4ac/m6SpPSYVJ7/RtLA8XstTPgAAAAAAAAAArZolPvDdhD4bgIm+e5QDv1EsyD3wABC+AAAAAAAAAABNMyq9Bcmwu94rfDtiDyI9K8ObvPAPXz0AAIA/AACAP5prLL0fVbq5xUn5vfNiBLNMHYC74EflMgAAgD8AAAAAAFDVOikOKT2D/mG+zM4wvvl0ub2SOn+9AAAAAAAAAAAz1zi9goT/Pitm5DsJTy2/duG2vVOChjsAAAAAAAAAAK15Zz6Y2AA/xiYIvUBdKr8aB4w+cK/9vQAAAAAAAAAAzYXmPPbMCbpK06y6vDOUNNi4ZLsh9so5AACAPwAAgD/NvpU8BcDXuy/RiT3uU249Tn48vQC+2boAAIA/AACAPwCP87z2lDi68tRKPeV0H7ad8v04zYwatQAAgD8AAIA/APzbu65xvbqfebm2C1StsTM5qDmy1dU1AACAPwAAgD9tPQo+ogOcP3JDfj6H1D6/KlUOPv2TTj4AAAAAAAAAAAC45Tyuj5O6qq4Ts7P7QjFaKgc7aiGzMwAAgD8AAIA/M6OeOo8OfbrKFko2DwNIMfGJ4LnDdnG1AACAPwAAgD/NFMK7j+ZuutXfRzpe0281iQaQOi0SZrkAAIA/AACAP8Dmhz0fe/I6DtbKvW5uAjwG/1S83ngquwAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -41,17 +41,17 @@
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.007616000000000067,
+    "_current_progress_remaining": 0.983616,
     "_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": 2460,
+    "_n_updates": 597,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -84,7 +84,7 @@
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
     "batch_size": 64,
-    "n_epochs": 20,
+    "n_epochs": 8,
     "clip_range": {
         ":type:": "<class 'function'>",
         ":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:c8e66bce8ec1afd866bb0900ca50c44f97f3c23ee361b919c99711ea783bbe99
+oid sha256:c6290137993b5c8dac394ecc7f17383b5e47ff6b9a6ff80d8fbfe816a9f2f1ac
 size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:880a5173d4469e4ccb9f70fe99b587e37e33981d9b6ec62366f4ad35c94db5db
+oid sha256:8e6da37fecddcdbe78cc458d7da32e33128ae3c140b0018776c9374623023b99
 size 43762

ppo-LunarLander-v2/system_info.txt

@@ -1,4 +1,4 @@
-- OS: Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023
+- OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
 - Python: 3.10.12
 - Stable-Baselines3: 2.0.0a5
 - PyTorch: 2.1.0+cu118

results.json

@@ -1 +1 @@
-{"mean_reward": 288.1830244, "std_reward": 22.721032849790433, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-12T16:51:29.078587"}
+{"mean_reward": 286.4216147, "std_reward": 14.547907975238463, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-12-13T19:11:15.219346"}