Upload PPO LunarLander-v2 model

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 2.26 +/- 47.99
+      value: 184.41 +/- 87.19
       name: mean_reward
       verified: false
 ---

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__firstlineno__": 390, "__doc__": "\nPolicy class for actor-critic algorithms (has both policy and value prediction).\nUsed 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 0x00000224A62EA700>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x00000224A62EA7A0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x00000224A62EA840>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x00000224A62EA8E0>", "_build": "<function ActorCriticPolicy._build at 0x00000224A62EA980>", "forward": "<function ActorCriticPolicy.forward at 0x00000224A62EAA20>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x00000224A62EAAC0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x00000224A62EAB60>", "_predict": "<function ActorCriticPolicy._predict at 0x00000224A62EAC00>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x00000224A62EACA0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x00000224A62EAD40>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x00000224A62EADE0>", "__static_attributes__": ["action_dist", "action_net", "activation_fn", "dist_kwargs", "features_dim", "features_extractor", "log_std", "log_std_init", "mlp_extractor", "net_arch", "optimizer", "ortho_init", "pi_features_extractor", "share_features_extractor", "use_sde", "value_net", "vf_features_extractor"], "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x00000224A617BA00>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 100352, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1761064791257128700, "learning_rate": 0.0003, "tensorboard_log": "./ppo_lunarlander_tensorboard/", "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlgAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAADNn6K9Xi6OPXCFSL20MeS9mdm5vVZygT0AAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsIhpSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0035199999999999676, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 490, "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:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "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": "Windows-10-10.0.19045-SP0 10.0.19045", "Python": "3.13.7", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.9.0+cpu", "GPU Enabled": "False", "Numpy": "2.3.4", "Cloudpickle": "3.1.1", "Gymnasium": "0.28.1"}}
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__firstlineno__": 390, "__doc__": "\nPolicy class for actor-critic algorithms (has both policy and value prediction).\nUsed 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 0x0000020F1A746700>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x0000020F1A7467A0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x0000020F1A746840>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x0000020F1A7468E0>", "_build": "<function ActorCriticPolicy._build at 0x0000020F1A746980>", "forward": "<function ActorCriticPolicy.forward at 0x0000020F1A746A20>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x0000020F1A746AC0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x0000020F1A746B60>", "_predict": "<function ActorCriticPolicy._predict at 0x0000020F1A746C00>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x0000020F1A746CA0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x0000020F1A746D40>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x0000020F1A746DE0>", "__static_attributes__": ["action_dist", "action_net", "activation_fn", "dist_kwargs", "features_dim", "features_extractor", "log_std", "log_std_init", "mlp_extractor", "net_arch", "optimizer", "ortho_init", "pi_features_extractor", "share_features_extractor", "use_sde", "value_net", "vf_features_extractor"], "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x0000020F1A64DE80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1001472, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1761065387680295100, "learning_rate": 0.0003, "tensorboard_log": "./ppo_lunarlander_tensorboard/", "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlgAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAzoga99kq8P3vICL+NCsI+MOBAPIqnv7wAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsIhpSMAUOUdJRSlC4="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksBhZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0014719999999999178, "_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": 4890, "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:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "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": "Windows-10-10.0.19045-SP0 10.0.19045", "Python": "3.13.7", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.9.0+cpu", "GPU Enabled": "False", "Numpy": "2.3.4", "Cloudpickle": "3.1.1", "Gymnasium": "0.28.1"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b303169af6579af4ab535cbb19dc5828e8bef4380f715e2ee9b46ce7f4430f1
-size 148321
+oid sha256:d9036089d57ba6383214fdc74e4137483fcd12f4004c8e5acb998e2ebbad1a28
+size 148328

ppo-LunarLander-v2/data

@@ -5,18 +5,18 @@
         "__module__": "stable_baselines3.common.policies",
         "__firstlineno__": 390,
         "__doc__": "\nPolicy class for actor-critic algorithms (has both policy and value prediction).\nUsed 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 0x00000224A62EA700>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x00000224A62EA7A0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x00000224A62EA840>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x00000224A62EA8E0>",
-        "_build": "<function ActorCriticPolicy._build at 0x00000224A62EA980>",
-        "forward": "<function ActorCriticPolicy.forward at 0x00000224A62EAA20>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x00000224A62EAAC0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x00000224A62EAB60>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x00000224A62EAC00>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x00000224A62EACA0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x00000224A62EAD40>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x00000224A62EADE0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x0000020F1A746700>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x0000020F1A7467A0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x0000020F1A746840>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x0000020F1A7468E0>",
+        "_build": "<function ActorCriticPolicy._build at 0x0000020F1A746980>",
+        "forward": "<function ActorCriticPolicy.forward at 0x0000020F1A746A20>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x0000020F1A746AC0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x0000020F1A746B60>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x0000020F1A746C00>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x0000020F1A746CA0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x0000020F1A746D40>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x0000020F1A746DE0>",
         "__static_attributes__": [
             "action_dist",
             "action_net",
@@ -37,21 +37,21 @@
             "vf_features_extractor"
         ],
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x00000224A617BA00>"
+        "_abc_impl": "<_abc._abc_data object at 0x0000020F1A64DE80>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 100352,
-    "_total_timesteps": 100000,
+    "num_timesteps": 1001472,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1761064791257128700,
+    "start_time": 1761065387680295100,
     "learning_rate": 0.0003,
     "tensorboard_log": "./ppo_lunarlander_tensorboard/",
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlgAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAADNn6K9Xi6OPXCFSL20MeS9mdm5vVZygT0AAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsIhpSMAUOUdJRSlC4="
+        ":serialized:": "gAWVlgAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWIAAAAAAAAAAzoga99kq8P3vICL+NCsI+MOBAPIqnv7wAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJLAUsIhpSMAUOUdJRSlC4="
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -61,17 +61,17 @@
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.0035199999999999676,
+    "_current_progress_remaining": -0.0014719999999999178,
     "_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": 490,
+    "_n_updates": 4890,
     "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 sha256:3ec609aad7a4cd6d88e88a4bdf02b7eda06bf7e69b89509e4d77959856d32662
+oid sha256:79d93a629989747c778a23d055832bfb043584a342101860e6c24743e3fe0a0b
 size 88375

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d3c2b75b3b8dcac91dbf16308108fee55f0d8b2005a8a1b782fcbdd269144d6
+oid sha256:ba404836f9f995c77fb64ec5b5f9e4308d7736cf9da6fba375591b8cfb839ea8
 size 43967

results.json

@@ -1 +1 @@
-{"mean_reward": 2.260618399999998, "std_reward": 47.994930454878656, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-10-22T00:44:54.235387"}
+{"mean_reward": 184.40754429999998, "std_reward": 87.19100897428443, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-10-22T01:07:02.714950"}