Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -293.05 +/- 120.70
+      value: 219.04 +/- 72.74
       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 0x7ac223c23910>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ac223c239a0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ac223c23a30>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ac223c23ac0>", "_build": "<function ActorCriticPolicy._build at 0x7ac223c23b50>", "forward": "<function ActorCriticPolicy.forward at 0x7ac223c23be0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ac223c23c70>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ac223c23d00>", "_predict": "<function ActorCriticPolicy._predict at 0x7ac223c23d90>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ac223c23e20>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ac223c23eb0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ac223c23f40>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ac223d77980>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1024, "_total_timesteps": 1000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1731146177756491967, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAPpndb7iHZU/fBAEv4lbDb9Hf8o8o2tsvgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.02400000000000002, "_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": 4, "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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "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:": "gAWVrQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUaACMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFowEZnVuY5SMDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.5.0+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.0", "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 0x7eb642007400>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7eb642007490>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7eb642007520>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7eb6420075b0>", "_build": "<function ActorCriticPolicy._build at 0x7eb642007640>", "forward": "<function ActorCriticPolicy.forward at 0x7eb6420076d0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7eb642007760>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7eb6420077f0>", "_predict": "<function ActorCriticPolicy._predict at 0x7eb642007880>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7eb642007910>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7eb6420079a0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7eb642007a30>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7eb642195840>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 733533, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1731147705014408362, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAADp+rzsno276iOSO2MqDz3O4tG8VpvtPQAAgD8AAIA/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": 0.26681600000000005, "_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": 2868, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":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]", "_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:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "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:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.5.0+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.0", "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:cf62d0d7f692728b026ce0d7202fb6c4bc00785a3f96b173d4ace9a886026e7d
-size 143658
+oid sha256:893d5521cf08173f4f0f6edcc98756ec8cca8c166c7e67ac5301869ea20e0684
+size 147357

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 0x7ac223c23910>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ac223c239a0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ac223c23a30>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ac223c23ac0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7ac223c23b50>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7ac223c23be0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ac223c23c70>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ac223c23d00>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7ac223c23d90>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ac223c23e20>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ac223c23eb0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ac223c23f40>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7eb642007400>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7eb642007490>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7eb642007520>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7eb6420075b0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7eb642007640>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7eb6420076d0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7eb642007760>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7eb6420077f0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7eb642007880>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7eb642007910>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7eb6420079a0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7eb642007a30>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7ac223d77980>"
+        "_abc_impl": "<_abc._abc_data object at 0x7eb642195840>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 1024,
-    "_total_timesteps": 1000,
+    "num_timesteps": 733533,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1731146177756491967,
+    "start_time": 1731147705014408362,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAPpndb7iHZU/fBAEv4lbDb9Hf8o8o2tsvgAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAADp+rzsno276iOSO2MqDz3O4tG8VpvtPQAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -41,17 +41,17 @@
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.02400000000000002,
+    "_current_progress_remaining": 0.26681600000000005,
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "gAWVQgwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHBU5jQRf4SMAWyUTVgBjAF0lEdAk9fQEQoTf3V9lChoBkdAcLoea8YhuGgHTVIBaAhHQJPZst9QXRB1fZQoaAZHQDdyJqIrOJNoB00RAWgIR0CT3HFB6a9cdX2UKGgGR0BvTXNLUTcqaAdNZQFoCEdAk95z2zv7WXV9lChoBkdAcEelf7aZhWgHTUQBaAhHQJPgN/G2kSF1fZQoaAZHQHIYAGfPHDJoB00iAWgIR0CT4xDA8B+4dX2UKGgGR0BIIfSx7iQ1aAdNXAFoCEdAk+VCp71Iy3V9lChoBkdAcKHTMqz7dmgHTS4BaAhHQJPm9d4Vym11fZQoaAZHQHDtUFB6a9doB02QAWgIR0CT6mvAoG6gdX2UKGgGR0Bu+WOOsDGMaAdNbgFoCEdAk+yHx8UmD3V9lChoBkdAbjY/8EV32WgHTV4BaAhHQJPudbaAWi11fZQoaAZHQHEoemJm/WVoB00zAWgIR0CT8WCtihFmdX2UKGgGR0BxYGTaCcwyaAdNPAFoCEdAk/M0mMOwxHV9lChoBkfAB3OzposZpGgHTUMBaAhHQJP1AvkBCD51fZQoaAZHQHBitWuHN5doB01MAWgIR0CT9/3Zf2K3dX2UKGgGR0BJyLS/j81oaAdNQwFoCEdAk/nEXP7emHV9lChoBkdAL9fNiYsunWgHTQkBaAhHQJP7QQtjCpF1fZQoaAZHQG9xGLcbiqBoB01DAWgIR0CT/Q1BMSK4dX2UKGgGR0Brj8oOQQtjaAdNVgFoCEdAlADZLVWjoXV9lChoBkdAb0/Pj4pMH2gHTW0BaAhHQJQDfbuc+aB1fZQoaAZHQG5xlsHjZL9oB01MAWgIR0CUBhWd3B55dX2UKGgGR0Bu1tk6Lfk4aAdNTAFoCEdAlAnvqPfbbnV9lChoBkdAIUEYO2AoX2gHTSQBaAhHQJQLg1fmcON1fZQoaAZHQHAC0+PikwhoB02EAWgIR0CUDaTDfm9ydX2UKGgGR0Bsx2K0lZ5iaAdNcwFoCEdAlBD8r3CbdHV9lChoBkdAbYMnjQzDXWgHTV8BaAhHQJQTCGmDUVl1fZQoaAZHQHCMPIn0CihoB01xAWgIR0CUFkRA8jiXdX2UKGgGR0A4FFC9h7VsaAdNGgFoCEdAlBfNQwblzXV9lChoBkdAcWwatLcsUmgHTYEBaAhHQJQZ5vo/zJ91fZQoaAZHQHC4cMiKR+1oB01RAWgIR0CUG7bm2b5NdX2UKGgGR0BvyxIlMRHxaAdNZQFoCEdAlB7Sw8nuzHV9lChoBkdAa0+/TspobmgHTVoBaAhHQJQgxSFXaJ11fZQoaAZHQHD/AHJLdvdoB008AWgIR0CUInzeoDPodX2UKGgGR0BMUMuWa+ewaAdNNQFoCEdAlCVjByjpLXV9lChoBkdAcWSIyj59E2gHTTYBaAhHQJQnD9GZuyh1fZQoaAZHQGwhoznA6+5oB01HAWgIR0CUKOhBqsU7dX2UKGgGR0BxNv7hvR7aaAdNUAFoCEdAlCvp2IO6NHV9lChoBkdAcWQIcBEKE2gHTTABaAhHQJQtl/+bVjJ1fZQoaAZHP956QeV9nbtoB0vyaAhHQJQu6FpPAO91fZQoaAZHQHBjI6jnFHdoB00qAWgIR0CUMho8IRh+dX2UKGgGR0Bydhic5Ke1aAdNgwFoCEdAlDTAYHgP3HV9lChoBkdAcXHocaOxS2gHTUMBaAhHQJQ3RZbILgJ1fZQoaAZHQHChBIz3yqdoB01fAWgIR0CUO8dv863idX2UKGgGR0BtmjUy57PZaAdNTQFoCEdAlD7HV5KODXV9lChoBkdAKf26shgVoGgHTT0BaAhHQJRAhyuIRAd1fZQoaAZHQEPkKF7D2rZoB0v6aAhHQJRCaR2bG3p1fZQoaAZHQBXm+bmU4aRoB00PAWgIR0CUR8Q+2VmjdX2UKGgGR0BwMnxwyZa3aAdNhgFoCEdAlExQ08/2TXV9lChoBkdAbaHA7gbZOGgHTT4BaAhHQJRPgnOSntR1fZQoaAZHQHGG6iO/+KloB02VAWgIR0CUU7itaIN3dX2UKGgGR0ByQVu4wyqNaAdNjQFoCEdAlFXtrKvFFXV9lChoBkdAbZ72q1gH/2gHTVEBaAhHQJRY941P3zt1fZQoaAZHQHC+uZCv5gxoB01hAWgIR0CUWvda+vhZdX2UKGgGR0BuAGtKZlWfaAdNawFoCEdAlF0POhTOxHV9lChoBkdAb9wplSS/02gHTVsBaAhHQJRgQNkOI691fZQoaAZHwD3hqcmShaloB00DAWgIR0CUYauhbnoxdX2UKGgGR0BJ3Z6MR6F/aAdNEQFoCEdAlGMvywwCbXV9lChoBkdAcDw80DU3GWgHTUMBaAhHQJRlgCOmzjZ1fZQoaAZHQFETSnLq2SdoB00EAWgIR0CUaPjOcDr7dX2UKGgGR0Bx2yYsunMuaAdNSAFoCEdAlGuPSH/LknV9lChoBkdAcJhcm0E5hmgHTUABaAhHQJRt+cmShal1fZQoaAZHQG4Sjps41gpoB01UAWgIR0CUcRKWcBludX2UKGgGR0BvMbNt65XmaAdNYQFoCEdAlHMFTR6WxHV9lChoBkdAcKrC9ytFKGgHTV8BaAhHQJR05lXiiqR1fZQoaAZHQHBo8kIHC41oB01SAWgIR0CUd/s052hadX2UKGgGR0Bo88TSLIgeaAdN4wFoCEdAlHqnenAIp3V9lChoBkdAbrULmZE2HmgHTWwBaAhHQJR8qoOx0Mh1fZQoaAZHQHCcfqHGjsVoB01NAWgIR0CUf7gjyFwldX2UKGgGR0Bx1kKu0TlDaAdNdwFoCEdAlIHGdVea8nV9lChoBkdAP5rELpiZv2gHTRkBaAhHQJSDV7CzkZJ1fZQoaAZHQG+mNyPuG9JoB01ZAWgIR0CUhmkn1FpgdX2UKGgGR0BwlvHJcPe6aAdNQQFoCEdAlIg1sDW9UXV9lChoBkdAcYOpMpPRA2gHTVIBaAhHQJSKHmA9V3l1fZQoaAZHQHBP01ZTyaxoB01dAWgIR0CUjU5xR2r5dX2UKGgGR0BrCwzDXOGCaAdNXAFoCEdAlI9Dt9hJAnV9lChoBkdAcR0JfpljE2gHTWgBaAhHQJSRSwD/2kB1fZQoaAZHQHCbKhUR3/xoB01mAWgIR0CUlISofjjrdX2UKGgGR0BskNI3BHkMaAdNOQFoCEdAlJZ4vnKW9nV9lChoBkdAcfd38XN1Q2gHTWoBaAhHQJSZBY8uBc11fZQoaAZHQG6TK8tf5UNoB01PAWgIR0CUnTNyYG+sdX2UKGgGR0Bw6SPjn3cpaAdNlQFoCEdAlKBJ3gUDdXV9lChoBkdAbdbtUn5SFWgHTW0BaAhHQJSjvHEMspZ1fZQoaAZHQHFcXNs3yZtoB01vAWgIR0CUpcn62v0RdX2UKGgGR0BwIAtsenyeaAdNVAFoCEdAlKejMqz7dnV9lChoBkdAcdU97F85S2gHTW0BaAhHQJSq0ZUDMeR1fZQoaAZHQG6wVZs9B8hoB01OAWgIR0CUrLCP6sQvdX2UKGgGR0BwWNFEy+HraAdNQQFoCEdAlK5zAeq7y3V9lChoBkdAbws0dBBzFWgHTWcBaAhHQJSxo/wAlv91fZQoaAZHQG/2HVf/m1ZoB016AWgIR0CUs8BmPHT7dX2UKGgGR0BHpz0HyEteaAdNFAFoCEdAlLVON96Tn3V9lChoBkdAbL+llbu+iGgHTVIBaAhHQJS4WVUuL751fZQoaAZHQHBO8r7O3UhoB014AWgIR0CUunSZBsyjdX2UKGgGR0BxbFE+gUUPaAdNQgFoCEdAlLw5dGAkLXV9lChoBkdAbU2KzAvcrWgHTUMBaAhHQJS/NEG7jDN1fZQoaAZHQHCvgVXV9WpoB01dAWgIR0CUwTIkJKJ3dX2UKGgGR0BvgYEB8x9HaAdNdQFoCEdAlMM4gieNDXV9lChoBkdAcJrcDbJwKmgHTUsBaAhHQJTGRPrOZ9d1fZQoaAZHQGt4+Vkc0choB01GAWgIR0CUyBKUVzp5dX2UKGgGR0BsZ+IXTEzgaAdNTQFoCEdAlMo9oWYWtXV9lChoBkdAUOidMCcPOWgHTSUBaAhHQJTNsp3HJcR1ZS4="
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 4,
+    "_n_updates": 2868,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:331f05f15bca86fc13c46548dca54c21cff7e623ef9f74c8e956630b7624e5fd
+oid sha256:5284a57942c8ba4f348b155a8fcea8d76d9af2da34e6fbb6a86d6f634aeb542d
 size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7b7e5a6b3e80149f55e26e736e6ba162e4395186951e4581ed7aaaca2a130aa
+oid sha256:4eb72eb16907c99798c1b767caa0fc7198eba94ef496ca2c1456d12c3ef5069f
 size 43762

results.json

@@ -1 +1 @@
-{"mean_reward": -293.0495171256363, "std_reward": 120.69677841499188, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-09T10:12:50.180483"}
+{"mean_reward": 219.03637782754475, "std_reward": 72.73545824547772, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-09T10:46:02.842417"}