LunarLander improved

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 220.82 +/- 67.08
+      value: 256.03 +/- 31.91
       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 0x7c5a146b5000>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c5a146b5090>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c5a146b5120>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c5a146b51b0>", "_build": "<function ActorCriticPolicy._build at 0x7c5a146b5240>", "forward": "<function ActorCriticPolicy.forward at 0x7c5a146b52d0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c5a146b5360>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c5a146b53f0>", "_predict": "<function ActorCriticPolicy._predict at 0x7c5a146b5480>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c5a146b5510>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c5a146b55a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c5a146b5630>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c5a14659680>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1704949256753409069, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAKZnmb37wVY/wpaWvFKP077vwXG9ohkiuwAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.00044800000000000395, "_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": 3908, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "gAWVcAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoB4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoECiWCAAAAAAAAAABAQEBAQEBAZRoFEsIhZRoGHSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBAoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaApLCIWUaBh0lFKUjARoaWdolGgQKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgKSwiFlGgYdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=", "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": 1, "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": 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:": "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+cu121", "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 0x7d7aea795e10>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d7aea795ea0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d7aea795f30>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d7aea795fc0>", "_build": "<function ActorCriticPolicy._build at 0x7d7aea796050>", "forward": "<function ActorCriticPolicy.forward at 0x7d7aea7960e0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d7aea796170>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d7aea796200>", "_predict": "<function ActorCriticPolicy._predict at 0x7d7aea796290>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d7aea796320>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d7aea7963b0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d7aea796440>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d7af17a0e00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 100352, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1705032523010446447, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAOZ9NT1PVBq8/oNsvaogg74TTAC8tSjPvAAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0035199999999999676, "_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": 4380, "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": 4, "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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", "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/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "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+cu121", "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 sha256:7afbe7249db2389a56ff7eb3ec087d49d97407691a5650ce0bdd373341999821
-size 147382
+oid sha256:4e859d07cc6eef00d69d5723d110e30da47fa1e8cb762b57ceb0a47ae0726295
+size 147583

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 0x7c5a146b5000>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c5a146b5090>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c5a146b5120>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c5a146b51b0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7c5a146b5240>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7c5a146b52d0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c5a146b5360>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c5a146b53f0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7c5a146b5480>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c5a146b5510>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c5a146b55a0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c5a146b5630>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7d7aea795e10>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d7aea795ea0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d7aea795f30>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d7aea795fc0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7d7aea796050>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7d7aea7960e0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d7aea796170>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d7aea796200>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7d7aea796290>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d7aea796320>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d7aea7963b0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d7aea796440>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7c5a14659680>"
+        "_abc_impl": "<_abc._abc_data object at 0x7d7af17a0e00>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 1000448,
-    "_total_timesteps": 1000000,
+    "num_timesteps": 100352,
+    "_total_timesteps": 100000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1704949256753409069,
+    "start_time": 1705032523010446447,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAKZnmb37wVY/wpaWvFKP077vwXG9ohkiuwAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAOZ9NT1PVBq8/oNsvaogg74TTAC8tSjPvAAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -41,20 +41,35 @@
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.00044800000000000395,
+    "_current_progress_remaining": -0.0035199999999999676,
     "_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": 3908,
+    "_n_updates": 4380,
+    "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": 4,
+    "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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",
+        ":serialized:": "gAWVdgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAAC0wgAAtMIAAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAtEIAALRCAACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFtbLTkwLiAgICAgICAgLTkwLiAgICAgICAgIC01LiAgICAgICAgIC01LiAgICAgICAgIC0zLjE0MTU5MjcgIC01LgogIC0wLiAgICAgICAgIC0wLiAgICAgICBdlIwJaGlnaF9yZXBylIxTWzkwLiAgICAgICAgOTAuICAgICAgICAgNS4gICAgICAgICA1LiAgICAgICAgIDMuMTQxNTkyNyAgNS4KICAxLiAgICAgICAgIDEuICAgICAgIF2UjApfbnBfcmFuZG9tlE51Yi4=",
         "dtype": "float32",
         "bounded_below": "[ True  True  True  True  True  True  True  True]",
         "bounded_above": "[ True  True  True  True  True  True  True  True]",
@@ -69,7 +84,7 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
+        ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
         "n": "4",
         "start": "0",
         "_shape": [],
@@ -77,21 +92,6 @@
         "_np_random": null
     },
     "n_envs": 1,
-    "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": 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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"

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:702a32d874842c6aaff60bdb0c7ad897c43fc1e89872c9fb15816e1dd25f2701
-size 88362
+oid sha256:256f21f29169c7eb78bbb28e302f729880ec0980b652d7331a39ea0242ed3e1f
+size 88490

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1c28bf009a2b51ed7467e196d01e40d36371f481440a1133ce645bad9b92bc1
+oid sha256:561e64e1690ee99b4e1d6200a12dfa1e862170b346f3beca14136e3ab0c06561
 size 43762

results.json

@@ -1 +1 @@
-{"mean_reward": 220.8212657090643, "std_reward": 67.08220848887667, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-11T06:16:27.051348"}
+{"mean_reward": 256.0329117080167, "std_reward": 31.912376540123173, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-12T04:17:51.352900"}