Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 237.63 +/- 76.48
+      value: 287.44 +/- 17.27
       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 0x7e9a5e7a5d80>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e9a5e7a5e10>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e9a5e7a5ea0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e9a5e7a5f30>", "_build": "<function ActorCriticPolicy._build at 0x7e9a5e7a5fc0>", "forward": "<function ActorCriticPolicy.forward at 0x7e9a5e7a6050>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e9a5e7a60e0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e9a5e7a6170>", "_predict": "<function ActorCriticPolicy._predict at 0x7e9a5e7a6200>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e9a5e7a6290>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e9a5e7a6320>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e9a5e7a63b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e9a5e7ac700>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1700864, "_total_timesteps": 1700000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1718544560315957358, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAHNUJL5DcXe8nnpAu7//i7k1Z+89tv2GOgAAgD8AAIA/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": -0.0005082352941176982, "_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": 11416, "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:": "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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 Sun Apr 28 14:29:16 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "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 0x7da8a54d0d30>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7da8a54d0dc0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7da8a54d0e50>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7da8a54d0ee0>", "_build": "<function ActorCriticPolicy._build at 0x7da8a54d0f70>", "forward": "<function ActorCriticPolicy.forward at 0x7da8a54d1000>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7da8a54d1090>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7da8a54d1120>", "_predict": "<function ActorCriticPolicy._predict at 0x7da8a54d11b0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7da8a54d1240>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7da8a54d12d0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7da8a54d1360>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7da8a546e040>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1701888, "_total_timesteps": 1700000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1718791812799516113, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAABqTJj1Xh0k8/6mAvkTf9L3HGsa9odYsvAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.0011105882352941965, "_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": 4155, "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": 2048, "gamma": 0.999, "gae_lambda": 0.97, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 78, "n_epochs": 5, "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 Sun Apr 28 14:29:16 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.3.0+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "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 sha256:64524ad9a4417ae9c883a91ec71d18254c00296e0388b4037bedc1e2c66a1dea
-size 147322
+oid sha256:b7c7d36e4a3df8aa044af812eb65795cc2917786df2c4187324e859168032fdc
+size 147301

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 0x7e9a5e7a5d80>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7e9a5e7a5e10>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7e9a5e7a5ea0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7e9a5e7a5f30>",
-        "_build": "<function ActorCriticPolicy._build at 0x7e9a5e7a5fc0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7e9a5e7a6050>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7e9a5e7a60e0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7e9a5e7a6170>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7e9a5e7a6200>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7e9a5e7a6290>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7e9a5e7a6320>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7e9a5e7a63b0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7da8a54d0d30>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7da8a54d0dc0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7da8a54d0e50>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7da8a54d0ee0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7da8a54d0f70>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7da8a54d1000>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7da8a54d1090>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7da8a54d1120>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7da8a54d11b0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7da8a54d1240>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7da8a54d12d0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7da8a54d1360>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7e9a5e7ac700>"
+        "_abc_impl": "<_abc._abc_data object at 0x7da8a546e040>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 1700864,
+    "num_timesteps": 1701888,
     "_total_timesteps": 1700000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1718544560315957358,
+    "start_time": 1718791812799516113,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAHNUJL5DcXe8nnpAu7//i7k1Z+89tv2GOgAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAABqTJj1Xh0k8/6mAvkTf9L3HGsa9odYsvAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.0005082352941176982,
+    "_current_progress_remaining": -0.0011105882352941965,
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "gAWV5QsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHN7yg00m+mMAWyUS9OMAXSUR0CpI39eY2KmdX2UKGgGR0BvG/R9gF5faAdL0mgIR0CpJBz19ORDdX2UKGgGR0BuxHXRPXTWaAdL7mgIR0CpJMs9bHIZdX2UKGgGR0BzpgK1G9YfaAdL+WgIR0CpJYLHlwLmdX2UKGgGR0Bwi9X4j8k2aAdLzmgIR0CpJhrNGEwndX2UKGgGR0ByvLgl4TsZaAdNKAFoCEdAqSb48hcJMXV9lChoBkdAZZzEk0JnhGgHTegDaAhHQKkrP4fwI+p1fZQoaAZHQHFGRnjABT5oB0vFaAhHQKkrzLDAJsx1fZQoaAZHQG4bCBf8dghoB0vFaAhHQKksYiDdxhl1fZQoaAZHQHI2LRa5f+loB0vMaAhHQKks/DuSfUZ1fZQoaAZHQHEOYL9deIFoB0vfaAhHQKktoi5/b0x1fZQoaAZHQHKFDw6QvHtoB0vqaAhHQKkudRnezld1fZQoaAZHQHJ9yKNyYHBoB0vFaAhHQKkw5QID5j91fZQoaAZHQHD9/5ckdFRoB0u/aAhHQKkxqqaPS2J1fZQoaAZHQHISEKmbb11oB0vcaAhHQKkykAG0NSZ1fZQoaAZHQHE6CU5dWyVoB0u3aAhHQKkzRqxkd3l1fZQoaAZHQHJQfo7muDBoB0vkaAhHQKk0KpxWDHx1fZQoaAZHQHFpUp3HJcRoB0vdaAhHQKk091q33Ht1fZQoaAZHQHJLVvuPV/doB0vcaAhHQKk1mGs3hn91fZQoaAZHQHDvIBFNL15oB0vnaAhHQKk2PyjHn2Z1fZQoaAZHQG/AAqmTC+FoB0vGaAhHQKk20hf0Eox1fZQoaAZHQFIAiZv1lGxoB0uIaAhHQKk3NwcYIjZ1fZQoaAZHQFEHVB2OhkBoB0uYaAhHQKk5AaNMoMN1fZQoaAZHQG7nP/JeVs1oB0vUaAhHQKk5re67NB51fZQoaAZHQG38KGcnVoZoB0viaAhHQKk6VSJCSid1fZQoaAZHQHDVXNcGC7NoB0vYaAhHQKk6+qRU3n91fZQoaAZHQHDAE4NqgyxoB0vUaAhHQKk7kvM8ox51fZQoaAZHQGixiyhSLqFoB03oA2gIR0CpPnzoEB8ydX2UKGgGR0BnUMYZVGTcaAdN6ANoCEdAqULYljVhC3V9lChoBkdAcfcZ8rqdH2gHS9hoCEdAqUN5KODJ2nV9lChoBkdAcepBAOavzWgHS9VoCEdAqUQWZAprlHV9lChoBkdAby5Gza9K3GgHS89oCEdAqUSti8WbgHV9lChoBkdAcKrZowmE5GgHS9poCEdAqUVTI/7iynV9lChoBkdAcOk5c1O0s2gHS+xoCEdAqUYBAdGRWHV9lChoBkdAcd8DmKZUk2gHS8JoCEdAqUfxAQg9vHV9lChoBkdAcYD85jpcHGgHS8poCEdAqUiDXjENv3V9lChoBkdAcevdPLxI8WgHS91oCEdAqUlqP8yeqnV9lChoBkdAcnbVk+X7cmgHS9VoCEdAqUoyuEEkjXV9lChoBkdAUwRIH1OCXmgHS69oCEdAqUrOzposZ3V9lChoBkdActlmgam4zGgHS8FoCEdAqUuQlUp/gHV9lChoBkdActqmapgkT2gHS+JoCEdAqUx5a1TisHV9lChoBkdAcfG1G9YfXGgHS8JoCEdAqU1JB7eEZnV9lChoBkdAcrBCyyD7ImgHS9toCEdAqU40078vVXV9lChoBkdAcc8EGqxTsWgHS8BoCEdAqU7cfozN2XV9lChoBkdAcjQDXOGCZmgHS99oCEdAqVDuapgkT3V9lChoBkdAcO/NmUW2w2gHS+VoCEdAqVGxGBnSOXV9lChoBkdAbwkqmTC+DmgHS+hoCEdAqVJh/I8yOHV9lChoBkdAb0JmWdEsrmgHS/hoCEdAqVMbHlwLmnV9lChoBkdAcotZKWcBl2gHS9hoCEdAqVO+CsfaH3V9lChoBkdAcgVlcQiA2GgHS9FoCEdAqVRYOlO45XV9lChoBkdAcYzTFERao2gHS+NoCEdAqVUAaWHDaXV9lChoBkdAc3ue7cwg1WgHS8doCEdAqVWYpQUHp3V9lChoBkdAcIGF+d9Uj2gHS85oCEdAqVYugnMMZ3V9lChoBkdAcSZpSaVlgGgHS+poCEdAqVgmyzHCGnV9lChoBkdAcUq+A3DNyGgHS9poCEdAqVjIsEq2B3V9lChoBkdAcPVre67NCGgHS8ZoCEdAqVlbxEv0y3V9lChoBkdAckfY7JW/8GgHS+1oCEdAqVoMnAqNInV9lChoBkdAcY3t/nW8RWgHS9toCEdAqVqsQVbiZXV9lChoBkdAcsRQokRjBmgHS/VoCEdAqVtjr7fpEHV9lChoBkdAbfpV2icoY2gHS9JoCEdAqVwCX+l0o3V9lChoBkdAch6GnGbTdGgHS8NoCEdAqVyQL3K0U3V9lChoBkdAc1UvkzXSSmgHS9NoCEdAqV0zJ8v25HV9lChoBkdAcDaTTfBN22gHS9RoCEdAqV8eDJ2dNHV9lChoBkdAcHilWwNb1WgHS9JoCEdAqV/EvkBCD3V9lChoBkdAb0XuIhyKemgHS8ZoCEdAqWBYXKr7wnV9lChoBkdAck1bNKRMe2gHS8VoCEdAqWDsc4o7WHV9lChoBkdAcrIaS9ugpWgHS89oCEdAqWGG3QUpNXV9lChoBkdAci+CQLeANGgHS/ZoCEdAqWJES/TLGXV9lChoBkdAcacY/3WWhWgHS8poCEdAqWMHo5ggHXV9lChoBkdAcvLWt2cJ+mgHS+BoCEdAqWPcD2alUXV9lChoBkdAch49MsYl6mgHS9NoCEdAqWSe/8EV33V9lChoBkdAcdnddE9dNWgHS/hoCEdAqWWc1l5GBnV9lChoBkdAcmpj/MnqmmgHS8toCEdAqWhYlSjxkXV9lChoBkdAcL/YgJTl1mgHS+doCEdAqWkzCJoCdXV9lChoBkdAcujbyH2ys2gHS+loCEdAqWneD3/PxHV9lChoBkdAcZau5BkZrGgHS+NoCEdAqWqJamoBJnV9lChoBkdAb2fOX3QD3mgHS9poCEdAqWsnJ3gUDnV9lChoBkdAcc+tHQQcxWgHS81oCEdAqWvAwh4dIXV9lChoBkdAceE5hBqsVGgHS7JoCEdAqWxHXsgMdHV9lChoBkdAcS7fAsTWXmgHS8toCEdAqWzd/QSi/XV9lChoBkdAc83FCLMs6WgHS+9oCEdAqW2Q3aSLZXV9lChoBkdAbpJ8l5WzW2gHS8poCEdAqW4iih37lHV9lChoBkdAcIhx2St/4WgHS9toCEdAqXAHnB+F13V9lChoBkdAcv6P9kz412gHTQkBaAhHQKlwzZ7ojfN1fZQoaAZHQHJx7fxc3VFoB0vdaAhHQKlxbuv2XcB1fZQoaAZHQFLIDD0lJH1oB0ugaAhHQKlx4yY5T611fZQoaAZHQHDqXn2ZiNNoB0vnaAhHQKlykbIcR151fZQoaAZHQHIj05p8F6loB0vmaAhHQKlzPWrfcet1fZQoaAZHQG+atr9ETg5oB0vaaAhHQKlz3RLK3d91fZQoaAZHQHBKxoqTbFloB0vcaAhHQKl0gq//Nqx1fZQoaAZHQHFSOXNTtLNoB0vpaAhHQKl1LukUKzB1fZQoaAZHQHB9yV0Lc9JoB0vFaAhHQKl3Dv7WNFV1fZQoaAZHQG5pGw7kn1FoB0vdaAhHQKl3tI1+AmR1fZQoaAZHQHCkG/ag261oB0vVaAhHQKl4UbT+ee51fZQoaAZHQHKi1TisGPhoB0vyaAhHQKl5BooNNJx1fZQoaAZHQHHrN/z8P4FoB0vHaAhHQKl5nqv/zat1fZQoaAZHQHAOYuTRplBoB0v/aAhHQKl6WRnvlU91fZQoaAZHQHLN/Dxb0OFoB0vkaAhHQKl7AeT3Zf51fZQoaAZHQG/loIWxhUloB0vWaAhHQKl7nUvPC2t1fZQoaAZHQHLaSUTtb9toB0u3aAhHQKl8I5WBBiV1ZS4="
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 11416,
+    "_n_updates": 4155,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -77,14 +77,14 @@
         "_np_random": null
     },
     "n_envs": 1,
-    "n_steps": 1024,
+    "n_steps": 2048,
     "gamma": 0.999,
-    "gae_lambda": 0.98,
+    "gae_lambda": 0.97,
     "ent_coef": 0.01,
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
-    "batch_size": 64,
-    "n_epochs": 4,
+    "batch_size": 78,
+    "n_epochs": 5,
     "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 sha256:8ea27cc1779eb532b3799bbb0fa2350011a98a409345ed130da083fdcb2be7f8
+oid sha256:d07b10596057201002d926fb1125c10c6a6830eae7be3cdead00d4565c6b214d
 size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5bc19d0133b1fbd2629426c4e0fd196d54f794f1ddb22eb19df43df63621347
+oid sha256:9e1cc9bbd5c3257e67b924864de304c202644881d6fb4c68eddd47aa9ced8ff7
 size 43762

results.json

@@ -1 +1 @@
-{"mean_reward": 237.629491406449, "std_reward": 76.4836859978078, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-16T14:56:29.891170"}
+{"mean_reward": 287.44394208916543, "std_reward": 17.265674739977086, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-19T11:07:52.930284"}