1st reinforcement learning

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 267.93 +/- 15.90
+      value: 229.27 +/- 52.00
       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 0x7d0f1b848a60>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d0f1b848af0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d0f1b848b80>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d0f1b848c10>", "_build": "<function ActorCriticPolicy._build at 0x7d0f1b848ca0>", "forward": "<function ActorCriticPolicy.forward at 0x7d0f1b848d30>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d0f1b848dc0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d0f1b848e50>", "_predict": "<function ActorCriticPolicy._predict at 0x7d0f1b848ee0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d0f1b848f70>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d0f1b849000>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d0f1b849090>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d0ebdbf1380>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1736860129845623593, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_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": 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:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "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:": "gAWVrQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUaACMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFowEZnVuY5SMDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz/JmZmZmZmahZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "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": "2.5.1+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.0", "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 0x7b8619f02c00>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b8619f02ca0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b8619f02d40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b8619f02de0>", "_build": "<function ActorCriticPolicy._build at 0x7b8619f02e80>", "forward": "<function ActorCriticPolicy.forward at 0x7b8619f02f20>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b8619f02fc0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b8619f03060>", "_predict": "<function ActorCriticPolicy._predict at 0x7b8619f03100>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b8619f031a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b8619f03240>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b8619f032e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7b861a07d640>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1737195591597511589, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_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": 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:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "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-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.11.11", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.5.1+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.0", "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 sha256:335a71d2b44db3e2e43d27dd970577f65510248093aef12e2a5b9019ea4b4286
-size 147167
+oid sha256:98dfd9a722d5b3b2752319ce3bc938a0fd23e1f80b0ee650f1d1bf3075f2c7c5
+size 147348

ppo-LunarLander-v2/data

@@ -4,20 +4,20 @@
         ":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 0x7d0f1b848a60>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7d0f1b848af0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7d0f1b848b80>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7d0f1b848c10>",
-        "_build": "<function ActorCriticPolicy._build at 0x7d0f1b848ca0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7d0f1b848d30>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7d0f1b848dc0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7d0f1b848e50>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7d0f1b848ee0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7d0f1b848f70>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7d0f1b849000>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7d0f1b849090>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7b8619f02c00>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7b8619f02ca0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7b8619f02d40>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7b8619f02de0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7b8619f02e80>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7b8619f02f20>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7b8619f02fc0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7b8619f03060>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7b8619f03100>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7b8619f031a0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7b8619f03240>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7b8619f032e0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7d0ebdbf1380>"
+        "_abc_impl": "<_abc._abc_data object at 0x7b861a07d640>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -26,7 +26,7 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1736860129845623593,
+    "start_time": 1737195591597511589,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": null,
@@ -42,7 +42,7 @@
     "_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'>",
@@ -73,7 +73,7 @@
         "dtype": "int64",
         "_np_random": null
     },
-    "n_envs": 1,
+    "n_envs": 16,
     "n_steps": 2048,
     "gamma": 0.99,
     "gae_lambda": 0.95,
@@ -84,13 +84,13 @@
     "n_epochs": 10,
     "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:": "gAWV1gIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwiVAZcAiQFTAJROhZQpjAFflIWUjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjExL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUS4RDCPiAANgPEogKlEMAlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTEvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpRoAIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCF9lH2UKGgYjARmdW5jlIwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBmMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHPzOpKjBVMmGFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
     }
 }

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1608865402ce67ced6ee6f8b5389ddff5660282e8167adf7b3aebedbd9f09de3
+oid sha256:c2fb3ea4f946527ace63ce3cbb5903e21d6f82951bbda83ccfb3b9ad8040855a
 size 88490

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb089bef4f579c37c1201320db7a5541a099aceb478a6d4dbb883aaa23b32fe7
+oid sha256:13438bd1bbf58b2a53f72c505e23a29b3661734a7708d0a1da870747df590df7
 size 43762

ppo-LunarLander-v2/system_info.txt

@@ -1,5 +1,5 @@
 - 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
+- Python: 3.11.11
 - Stable-Baselines3: 2.0.0a5
 - PyTorch: 2.5.1+cu121
 - GPU Enabled: True

results.json

@@ -1 +1 @@
-{"mean_reward": 267.9340896, "std_reward": 15.90227899791083, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-14T13:50:53.496421"}
+{"mean_reward": 229.26862760000003, "std_reward": 51.99604117830228, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-01-18T10:47:09.047898"}