First train rl model

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 217.80 +/- 68.11
+      value: 287.12 +/- 22.56
       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 0x797404711300>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7974047113a0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x797404711440>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7974047114e0>", "_build": "<function ActorCriticPolicy._build at 0x797404711580>", "forward": "<function ActorCriticPolicy.forward at 0x797404711620>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7974047116c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x797404711760>", "_predict": "<function ActorCriticPolicy._predict at 0x797404711800>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7974047118a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x797404711940>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7974047119e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7974048ac640>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1746609249775778597, "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:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_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": 310, "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": 16, "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:": "gAWV1gIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwiVAZcAiQFTAJROhZQpjAFflIWUjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjExL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUS4RDCPiAANgPEogKlEMAlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTEvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpRoAIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCF9lH2UKGgYjARmdW5jlIwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBmMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHPzOpKjBVMmGFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="}, "system_info": {"OS": "Linux-6.1.123+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Mar 30 16:01:29 UTC 2025", "Python": "3.11.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.6.0+cu124", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.1", "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 0x78def070f2e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78def070f380>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78def070f420>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78def070f4c0>", "_build": "<function ActorCriticPolicy._build at 0x78def070f560>", "forward": "<function ActorCriticPolicy.forward at 0x78def070f600>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x78def070f6a0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78def070f740>", "_predict": "<function ActorCriticPolicy._predict at 0x78def070f7e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78def070f880>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78def070f920>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x78def070f9c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x78def0868940>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 2031616, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1746613052474049720, "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:": "gAWVhAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWEAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksQhZSMAUOUdJRSlC4="}, "_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": 620, "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": 16, "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": "Linux-6.1.123+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Mar 30 16:01:29 UTC 2025", "Python": "3.11.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.6.0+cu124", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.1", "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:bdd9c3ab7a4eae9dea56da3d1ff99428db3fe54dcfef9eb43d39b3fedd2dea80
-size 148075
+oid sha256:5f4553046a3e7f732fa47c3c9cbb7b699d65573d21ba9a6d10bd01d818e6f311
+size 148003

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 0x797404711300>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7974047113a0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x797404711440>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7974047114e0>",
-        "_build": "<function ActorCriticPolicy._build at 0x797404711580>",
-        "forward": "<function ActorCriticPolicy.forward at 0x797404711620>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7974047116c0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x797404711760>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x797404711800>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7974047118a0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x797404711940>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7974047119e0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x78def070f2e0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78def070f380>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78def070f420>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78def070f4c0>",
+        "_build": "<function ActorCriticPolicy._build at 0x78def070f560>",
+        "forward": "<function ActorCriticPolicy.forward at 0x78def070f600>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x78def070f6a0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78def070f740>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x78def070f7e0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78def070f880>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78def070f920>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x78def070f9c0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7974048ac640>"
+        "_abc_impl": "<_abc._abc_data object at 0x78def0868940>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 1015808,
-    "_total_timesteps": 1000000,
+    "num_timesteps": 2031616,
+    "_total_timesteps": 2000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1746609249775778597,
+    "start_time": 1746613052474049720,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -45,13 +45,13 @@
     "_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": 310,
+    "_n_updates": 620,
     "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 sha256:7fce3c31ef97a35884ff8112f5e810df7be6cd764ded1055bf842bbac2e5df9d
+oid sha256:02eb2ed8e723138c7e5425b4a4ab36ee313b0bd63f059e7bdc5a86dbbc3105f5
 size 88362

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce4beef800ce33bec2f745c520431000601acaa90d859dbeb381513c7731163a
+oid sha256:41f0aed61ccb5c0d4d3bff20b5768dc41e6106611461aa18bad699aa9e566b9f
 size 43762

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e55a912c8131b7a0c5d6e8a479f25589f453961239abab6e0d9d09ffb1922ca
-size 160725
+oid sha256:c0b1f76c30014f93c833536e1a5a02adf6981874f3f4105bc855b19954e53766
+size 167479

results.json

@@ -1 +1 @@
-{"mean_reward": 217.79503309999996, "std_reward": 68.11170443881365, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-05-07T10:09:08.186632"}
+{"mean_reward": 287.1174783, "std_reward": 22.557853684934994, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-05-07T11:53:44.897375"}