Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 261.08 +/- 17.98
+      value: 265.63 +/- 34.53
       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 0x7af052655fc0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7af052656050>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7af0526560e0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7af052656170>", "_build": "<function ActorCriticPolicy._build at 0x7af052656200>", "forward": "<function ActorCriticPolicy.forward at 0x7af052656290>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7af052656320>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7af0526563b0>", "_predict": "<function ActorCriticPolicy._predict at 0x7af052656440>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7af0526564d0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7af052656560>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7af0526565f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7af052660900>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1713535136139407003, "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": -0.015808000000000044, "_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": 252, "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": 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-6.1.58+-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": "2.2.1+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 0x14c96f5b0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x14c96f640>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x14c96f6d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x14c96f760>", "_build": "<function ActorCriticPolicy._build at 0x14c96f7f0>", "forward": "<function ActorCriticPolicy.forward at 0x14c96f880>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x14c96f910>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x14c96f9a0>", "_predict": "<function ActorCriticPolicy._predict at 0x14c96fa30>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x14c96fac0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x14c96fb50>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x14c96fbe0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x14c963ac0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 0.0, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1.0, "_stats_window_size": 100, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "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": 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": "macOS-14.4.1-arm64-arm-64bit Darwin Kernel Version 23.4.0: Fri Mar 15 00:12:37 PDT 2024; root:xnu-10063.101.17~1/RELEASE_ARM64_T6031", "Python": "3.10.14", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.2.2", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.28.1"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2b06ddb56dce1907d40d73c79865d95d675be60018f181c23e98056cb37fa02
-size 148084
+oid sha256:de3a4aba5cb4c82895c2e4bef34c683acd12c64234c61b07fa02f9854a8e6cde
+size 141951

ppo-LunarLander-v2/data

@@ -4,54 +4,42 @@
         ":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 0x7af052655fc0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7af052656050>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7af0526560e0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7af052656170>",
-        "_build": "<function ActorCriticPolicy._build at 0x7af052656200>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7af052656290>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7af052656320>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7af0526563b0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7af052656440>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7af0526564d0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7af052656560>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7af0526565f0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x14c96f5b0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x14c96f640>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x14c96f6d0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x14c96f760>",
+        "_build": "<function ActorCriticPolicy._build at 0x14c96f7f0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x14c96f880>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x14c96f910>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x14c96f9a0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x14c96fa30>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x14c96fac0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x14c96fb50>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x14c96fbe0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7af052660900>"
+        "_abc_impl": "<_abc._abc_data object at 0x14c963ac0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 1015808,
-    "_total_timesteps": 1000000,
+    "num_timesteps": 0,
+    "_total_timesteps": 0,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1713535136139407003,
+    "start_time": 0.0,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
-    "_last_obs": {
-        ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAJoTBrykNGG7CDNwPH9jOjxyOai887AjPQAAgD8AAIA/ZoahPFxbR7pO5tw6z/BmNvd4JTo1i/65AACAPwAAgD9NR/Q98AjnPsBG/Tx8i5m+HzF7PT0w+TwAAAAAAAAAAGbxqDwUMLE/DpLJPmdplL7e8oO7KYSAPQAAAAAAAAAAoJ8Hvg6IHT+2wL89FaeGvvn2Br36uHc9AAAAAAAAAAAzSSu+FzaVPzKugb6l4ea+jMM/vvK0sjwAAAAAAAAAAM3SozwLKbU/ERQpP//fHj3dC4e84xh+vQAAAAAAAAAAWl1kPmOhUD+ZUgW9h+awvrwsDz4WXn29AAAAAAAAAAAtcHi+WyT/vGXk7bvLs1i6Sn1fPm6OIzsAAIA/AACAP4AtTj3Sec674yHdulauhDwC8iK9MxVhPQAAgD8AAIA/xoGYvt+/Uj8Yn6u8AVa3vmqoPL56N748AAAAAAAAAADNVoM+c8ozP4oc7b1uHaa+O1YmPhjo870AAAAAAAAAAIDAgr2F8965IHddPORBCrZq94U6eQADtQAAAAAAAAAA2hgdvv0ACT9Oow4+PLm7vpBfpLs8RZw9AAAAAAAAAAAjbpo+ttRhPzYDZD7S0q2+A3SVPnVIz7wAAAAAAAAAAJqWmD0fRbW5I45POv0/2rUl0Ng7Mo51uQAAgD8AAIA/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="
-    },
-    "_last_episode_starts": {
-        ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
-    },
+    "_last_obs": null,
+    "_last_episode_starts": null,
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.015808000000000044,
+    "_current_progress_remaining": 1.0,
     "_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": 252,
+    "ep_info_buffer": null,
+    "ep_success_buffer": null,
+    "_n_updates": 0,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -87,13 +75,13 @@
     "n_epochs": 4,
     "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 sha256:9f1a7e7b9d06e1a6e7ad30366459fe01f601e18ef9747551b65d2beb2a775e3c
-size 88362
+oid sha256:978cf049f1bb1304a7277a2b12c0cad807a002c3f84eed03547e08e90ed149f9
+size 87978

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fb5f13a8a8c44dac59e5064d2ac354da86afc59bcc3e0a70b2391f7f96bbb1d
-size 43762
+oid sha256:f40947f434ff39eca6d7c012d692c93b93cc4dc31f52dd613b8bd0fe8aa3558c
+size 43634

ppo-LunarLander-v2/pytorch_variables.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+oid sha256:ebdad4b9cfe9cd22a3abadb5623bf7bb1f6eb2e408740245eb3f2044b0adc018
 size 864

ppo-LunarLander-v2/system_info.txt

@@ -1,9 +1,8 @@
-- 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
+- OS: macOS-14.4.1-arm64-arm-64bit Darwin Kernel Version 23.4.0: Fri Mar 15 00:12:37 PDT 2024; root:xnu-10063.101.17~1/RELEASE_ARM64_T6031
+- Python: 3.10.14
 - Stable-Baselines3: 2.0.0a5
-- PyTorch: 2.2.1+cu121
-- GPU Enabled: True
-- Numpy: 1.25.2
-- Cloudpickle: 2.2.1
+- PyTorch: 2.2.2
+- GPU Enabled: False
+- Numpy: 1.26.4
+- Cloudpickle: 3.0.0
 - Gymnasium: 0.28.1
-- OpenAI Gym: 0.25.2

results.json

@@ -1 +1 @@
-{"mean_reward": 261.0760248125298, "std_reward": 17.98326202008515, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-19T14:36:09.712671"}
+{"mean_reward": 265.6285147, "std_reward": 34.52520265301213, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-23T15:51:44.641539"}