Push LunarLander-v2 model

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 240.68 +/- 47.48
+      value: 153.25 +/- 64.73
       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 0x7a9c6e4965f0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7a9c6e496680>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7a9c6e496710>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7a9c6e4967a0>", "_build": "<function ActorCriticPolicy._build at 0x7a9c6e496830>", "forward": "<function ActorCriticPolicy.forward at 0x7a9c6e4968c0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7a9c6e496950>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7a9c6e4969e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7a9c6e496a70>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7a9c6e496b00>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7a9c6e496b90>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7a9c6e496c20>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7a9c6e492140>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 4000768, "_total_timesteps": 4000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1720425464250814299, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAO1eOz7cjKQ+O2arPbLJKL+UPPE9V6aFvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////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": -0.00019199999999996997, "_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": 15628, "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": 0.1, "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-5.15.154+-x86_64-with-glibc2.31 # 1 SMP Thu Jun 27 20:43:36 UTC 2024", "Python": "3.10.13", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.2", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1", "OpenAI Gym": "0.26.2"}}
+{"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 0x7c99090216c0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c9909021750>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c99090217e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c9909021870>", "_build": "<function ActorCriticPolicy._build at 0x7c9909021900>", "forward": "<function ActorCriticPolicy.forward at 0x7c9909021990>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c9909021a20>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c9909021ab0>", "_predict": "<function ActorCriticPolicy._predict at 0x7c9909021b40>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c9909021bd0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c9909021c60>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c9909021cf0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c9908fcc180>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 516096, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1720468572460921400, "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": -0.032192, "_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": 126, "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": 16, "n_steps": 1536, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.1, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 32, "n_epochs": 6, "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": "2.3.0+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:d767617ac842c8723244c31237287a6539651ac58a946f437d5e9f9337ba7beb
-size 147290
+oid sha256:86d79be212736eb6570b489988fe015edb12525e0aa21622cf8f59f6a0064a73
+size 147985

ppo-LunarLander-v2/data

@@ -4,54 +4,54 @@
         ":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 0x7a9c6e4965f0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7a9c6e496680>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7a9c6e496710>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7a9c6e4967a0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7a9c6e496830>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7a9c6e4968c0>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7a9c6e496950>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7a9c6e4969e0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7a9c6e496a70>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7a9c6e496b00>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7a9c6e496b90>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7a9c6e496c20>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7c99090216c0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7c9909021750>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7c99090217e0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7c9909021870>",
+        "_build": "<function ActorCriticPolicy._build at 0x7c9909021900>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7c9909021990>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7c9909021a20>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7c9909021ab0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7c9909021b40>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7c9909021bd0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7c9909021c60>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7c9909021cf0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7a9c6e492140>"
+        "_abc_impl": "<_abc._abc_data object at 0x7c9908fcc180>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 4000768,
-    "_total_timesteps": 4000000,
+    "num_timesteps": 516096,
+    "_total_timesteps": 500000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1720425464250814299,
+    "start_time": 1720468572460921400,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAO1eOz7cjKQ+O2arPbLJKL+UPPE9V6aFvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
     },
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.00019199999999996997,
+    "_current_progress_remaining": -0.032192,
     "_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": 15628,
+    "_n_updates": 126,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -76,24 +76,24 @@
         "dtype": "int64",
         "_np_random": null
     },
-    "n_envs": 1,
-    "n_steps": 1024,
+    "n_envs": 16,
+    "n_steps": 1536,
     "gamma": 0.999,
     "gae_lambda": 0.98,
     "ent_coef": 0.1,
     "vf_coef": 0.5,
     "max_grad_norm": 0.5,
-    "batch_size": 64,
-    "n_epochs": 4,
+    "batch_size": 32,
+    "n_epochs": 6,
     "clip_range": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":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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"
+        ":serialized:": "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"
     }
 }

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d2ee042b0712991b9dddcc6120d97dae80a850be93cbe14ec3dffa115ae33e5
+oid sha256:e81de07fd711118aafa4c283ef4e95dcc6f555ae108cc27635f5ad21bcb8ba9d
 size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33dfbe57e10ec6f1b86be1590aa4233e0f2dd9ef448ef34f85ed6dadbeb231bd
+oid sha256:75ad9bc17541eb7355403d029ef1c0776ccceed455cf5039fb8617cf9ef11456
 size 43762

ppo-LunarLander-v2/system_info.txt

@@ -1,9 +1,9 @@
-- OS: Linux-5.15.154+-x86_64-with-glibc2.31 # 1 SMP Thu Jun 27 20:43:36 UTC 2024
-- Python: 3.10.13
+- 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: 2.1.2
+- PyTorch: 2.3.0+cu121
 - GPU Enabled: True
-- Numpy: 1.26.4
-- Cloudpickle: 3.0.0
+- Numpy: 1.25.2
+- Cloudpickle: 2.2.1
 - Gymnasium: 0.28.1
-- OpenAI Gym: 0.26.2
+- OpenAI Gym: 0.25.2

results.json

@@ -1 +1 @@
-{"mean_reward": 240.6791363043787, "std_reward": 47.477489458548014, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-08T10:06:06.237999"}
+{"mean_reward": 153.2491425393251, "std_reward": 64.72712222858796, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-07-08T20:27:15.081546"}