Upload PPO LunarLander-v2 trained agent

PPO-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:685d773588208f74d02ccbb636e984e5fe7304a9799b389f8f9e7443565d864c
-size 150772
+oid sha256:d0d8146cbced5d0f55c8eda59eaabc68e115cf5fccc7dc6a235cf369d1db500b
+size 150335

PPO-LunarLander-v2/data

@@ -4,30 +4,30 @@
         ":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 0x7f5f535aa940>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f5f535aa9d0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5f535aaa60>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f5f535aaaf0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f5f535aab80>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f5f535aac10>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f5f535aaca0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5f535aad30>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f5f535aadc0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5f535aae50>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f5f535aaee0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5f535aaf70>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f911441c9d0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f911441ca60>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f911441caf0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f911441cb80>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f911441cc10>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f911441cca0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f911441cd30>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f911441cdc0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f911441ce50>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f911441cee0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f911441cf70>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9114421040>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f5f535abe00>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f911441e940>"
     },
     "verbose": 2,
     "policy_kwargs": {},
-    "num_timesteps": 100352,
-    "_total_timesteps": 100000,
+    "num_timesteps": 10240,
+    "_total_timesteps": 10000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1728980837447001577,
-    "learning_rate": 0.0001,
+    "start_time": 1728981878004589149,
+    "learning_rate": 0.0008,
     "tensorboard_log": null,
     "_last_obs": null,
     "_last_episode_starts": {
@@ -38,17 +38,17 @@
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.0035199999999999676,
+    "_current_progress_remaining": -0.02400000000000002,
     "_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": 2940,
+    "_n_updates": 300,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -86,17 +86,17 @@
         "__module__": "stable_baselines3.common.buffers",
         "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}",
         "__doc__": "\n    Rollout buffer used in on-policy algorithms like A2C/PPO.\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to classic advantage when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ",
-        "__init__": "<function RolloutBuffer.__init__ at 0x7f5f538bc9d0>",
-        "reset": "<function RolloutBuffer.reset at 0x7f5f538bca60>",
-        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7f5f538bcaf0>",
-        "add": "<function RolloutBuffer.add at 0x7f5f538bcb80>",
-        "get": "<function RolloutBuffer.get at 0x7f5f538bcc10>",
-        "_get_samples": "<function RolloutBuffer._get_samples at 0x7f5f538bcca0>",
+        "__init__": "<function RolloutBuffer.__init__ at 0x7f9114730a60>",
+        "reset": "<function RolloutBuffer.reset at 0x7f9114730af0>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7f9114730b80>",
+        "add": "<function RolloutBuffer.add at 0x7f9114730c10>",
+        "get": "<function RolloutBuffer.get at 0x7f9114730ca0>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x7f9114730d30>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f5f538b7f80>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f911472cdc0>"
     },
     "rollout_buffer_kwargs": {},
-    "batch_size": 34,
+    "batch_size": 96,
     "n_epochs": 30,
     "clip_range": {
         ":type:": "<class 'function'>",
@@ -107,6 +107,6 @@
     "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:f94d9820b07f34a270f92d5df22f4c8e94b5768b1e60e25761084a4bc3e1ed20
+oid sha256:e418b209ffadf240ec93df7d001b7fec5b0e863bc4f889593838c1eb8c4faa85
 size 88490

PPO-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19f1e27e4e5c379b0b6ff5871a8ea8e91e09da0b89244ae850628ff3292cb755
+oid sha256:fed10843a86c7d1eba3c06ba530d274f7186e6c58303267499907e2d2928f831
 size 43762

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 4.45 +/- 126.59
+      value: -736.57 +/- 243.59
       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 0x7f5f535aa940>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f5f535aa9d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f5f535aaa60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f5f535aaaf0>", "_build": "<function ActorCriticPolicy._build at 0x7f5f535aab80>", "forward": "<function ActorCriticPolicy.forward at 0x7f5f535aac10>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f5f535aaca0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f5f535aad30>", "_predict": "<function ActorCriticPolicy._predict at 0x7f5f535aadc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f5f535aae50>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f5f535aaee0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f5f535aaf70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f5f535abe00>"}, "verbose": 2, "policy_kwargs": {}, "num_timesteps": 100352, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1728980837447001577, "learning_rate": 0.0001, "tensorboard_log": null, "_last_obs": null, "_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": -0.0035199999999999676, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVNwwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQFA+YpUgjhWMAWyUTegDjAF0lEdAZEWZ3LV4HHV9lChoBkdAUg5TuOS4fGgHTegDaAhHQGTkdgfEGaB1fZQoaAZHwGA34WUKRdRoB03IAWgIR0BlV1fVqesgdX2UKGgGR0BkaDVhCtzTaAdN6ANoCEdAZe9xJ/XoT3V9lChoBkdAaFh3oLXtjWgHTZMCaAhHQGYPKc3EQ5F1fZQoaAZHQF9cbZezD4xoB03oA2gIR0BmpFMuez2OdX2UKGgGR0BigfsXzlLfaAdN6ANoCEdAZzpeHBUJfXV9lChoBkfANjFjiGWUr2gHS6ZoCEdAZ6TsTnJT2nV9lChoBkdAJovNeMQ2/GgHS99oCEdAZ60sNlRP43V9lChoBkdAQd7tzCDVY2gHS+poCEdAZ7aNKh+OO3V9lChoBkdAW3yfkFOfumgHTegDaAhHQGhO0fxMFll1fZQoaAZHQBKjreIl+mZoB0ulaAhHQGhVWDpTuOV1fZQoaAZHwA4hIvrWy1NoB0u3aAhHQGhcTuWrwOR1fZQoaAZHQFpe+2mYSg5oB03oA2gIR0Bo+HMjeKsNdX2UKGgGR0BioaLVFx4qaAdN6ANoCEdAaYzuhsZYP3V9lChoBkdAYTapjMFEA2gHTegDaAhHQGomEnb7CSB1fZQoaAZHQG1UWeYlY2doB017AWgIR0BqljXtjTa1dX2UKGgGR8AhWqEOAiFCaAdLt2gIR0BqnOP1ct5EdX2UKGgGR8AqTupCKJl8aAdNGAFoCEdAaqfTNMXaanV9lChoBkdAWrCrWAf+0mgHTegDaAhHQGs4R46fapR1fZQoaAZHQGHUCAtnPE9oB03oA2gIR0BrymJUHY6GdX2UKGgGR0BtGOby6MBIaAdN5wFoCEdAbEUV7hNucnV9lChoBkfAHvGax5cC5mgHS7JoCEdAbExh/Aj6e3V9lChoBkdAVMjKp1ie/mgHTegDaAhHQGziRH5Jsft1fZQoaAZHwBSlejVQQ+VoB0vGaAhHQGzqKBun/DN1fZQoaAZHQEEGcBEKE39oB03oA2gIR0BtgUO5J9RadX2UKGgGR0Bslj2vjfelaAdNbQFoCEdAbZMEjgQ6IXV9lChoBkfAPa/8Muvll2gHS95oCEdAbZwM6RyOrHV9lChoBkfAQfRLoOhCdGgHS+9oCEdAbgN+PRzBAXV9lChoBkfARilahYeT3mgHTRkBaAhHQG4PSRSxZ+x1fZQoaAZHQGdN//NqxkdoB03DAWgIR0BuI2+ZgG8mdX2UKGgGR8A9W8fV7Qb/aAdL7WgIR0BujqwY+B6KdX2UKGgGR0BwCREH+qBFaAdNcgFoCEdAbp3mwqy4WnV9lChoBkdAYyGPEsJ6Y2gHTXECaAhHQG8f3trsSkF1fZQoaAZHwAlBwuM+/xloB0v0aAhHQG8pQlruYyB1fZQoaAZHQGw3WzWwu/VoB02NAWgIR0BvOh9PUKAsdX2UKGgGR0BqxIL/jsD5aAdNCwFoCEdAb0TfaYeDF3V9lChoBkfAPPeBH09QoGgHS/toCEdAb66Kx9oexXV9lChoBkdAcCSJrtVrAWgHTVEBaAhHQG+83B55Z8t1fZQoaAZHQGsSL4Fiay9oB025AmgIR0BwHkyeqaPTdX2UKGgGR8BWzPCdjG1haAdNXQFoCEdAcCV7kXDWLHV9lChoBkdAaJUKYRdyDWgHTbQBaAhHQHBfqd1+y7h1fZQoaAZHQDonck+otMBoB01cAmgIR0BwbujsUqQSdX2UKGgGR8BRSNS2phnbaAdNLAFoCEdAcHUMrmQr+nV9lChoBkdAUkYWFev6j2gHTegDaAhHQHC+XAEdNnJ1fZQoaAZHQEbpllsguAZoB03oA2gIR0BxBZNsWO6vdX2UKGgGR8BVPfszEaVEaAdNCQJoCEdAcUIhllK9PHV9lChoBkfAW6ENLDhtL2gHTTMCaAhHQHFOEG/vfCR1fZQoaAZHQGOQKZlWfbtoB03DAmgIR0BxjjakAPupdX2UKGgGR0Bl20xGlQ/HaAdNgAJoCEdAcdF8x9G7SXV9lChoBkfAVYQ4Ia99MWgHTQgCaAhHQHHcqT0QK8d1fZQoaAZHwGiFSLhrFfloB02rAmgIR0ByG0ZVGTcJdX2UKGgGR0BD1LHuJDVpaAdN6ANoCEdAcmFqkdmxuHV9lChoBkfAY9XmYBvJimgHTZgDaAhHQHKoFGLDQ7d1fZQoaAZHwFqYkqMFUyZoB02hAmgIR0ByuPEaVD8cdX2UKGgGR0BY5zG1hLGraAdN9wJoCEdAcwDpsGgSOHV9lChoBkfAQdA3DNyHVWgHTegDaAhHQHNS4sEq2Bt1fZQoaAZHQGCg0lZ5iVloB03PA2gIR0Bzmm3pfQa8dX2UKGgGR8BaPdugpSaWaAdNnQJoCEdAc94/MW43FXV9lChoBkdAWM09lmOENGgHTeMDaAhHQHQmq1TisGR1fZQoaAZHwE2hfpD/lyRoB03oA2gIR0B0dyKuSwGGdX2UKGgGR8BeGP7iyY5UaAdN0ANoCEdAdL5daMaS93V9lChoBkdANguzposZpGgHTegDaAhHQHUH26bvw3J1fZQoaAZHQGTjV8Ti84BoB014AmgIR0B1GK+Eh7mddX2UKGgGR0AbZyWAwwj/aAdNtQFoCEdAdVD5uqFRHnV9lChoBkdAaFzNDc/MXGgHTUgCaAhHQHVhVanrIHV1fZQoaAZHQGWvz7MxGlRoB02HAmgIR0B1of0L+glGdX2UKGgGR0BN9hSk0rLAaAdNIgNoCEdAdeXrBj4Ho3V9lChoBkfAWWQood+5OWgHTZgCaAhHQHX1jC+De0p1fZQoaAZHQGZADPWxyGVoB01VAmgIR0B2N1PRArxzdX2UKGgGR0Bj3lNSIgvEaAdNXwJoCEdAdkVvttygf3V9lChoBkfAX4ScVgx8D2gHTbwCaAhHQHaKpPl+3H91fZQoaAZHwGkpvRqoIfNoB02wA2gIR0B20oxubZvldX2UKGgGR0Bkx8KLKmsOaAdNIANoCEdAdxj8yN4qw3V9lChoBkdAYRH5GBnSOWgHTYwCaAhHQHdb3RTjvNN1fZQoaAZHQF7l0rbxmTVoB01AA2gIR0B3chqoIfKZdX2UKGgGR8Bbrl/+bVjJaAdNaAJoCEdAd7RUR3/xUnV9lChoBkdAZ7J6X0Gu92gHTVoCaAhHQHfydP557gN1fZQoaAZHwF9veBQN0/5oB01HAmgIR0B4AS2OQyRCdX2UKGgGR0BjXFa2WpqAaAdNZwJoCEdAeEDrgOz6anV9lChoBkdAaL4pPRArx2gHTZoCaAhHQHhQt3Sro4d1fZQoaAZHwGacwf6oESxoB03yAmgIR0B4l2M5wOvudX2UKGgGR0BhLczoEB8yaAdNbgJoCEdAeNfa8Hv+fnV9lChoBkdAaZ62zfJmumgHTeYCaAhHQHjp/O2RaHN1fZQoaAZHQGjp3wLE1l5oB032AmgIR0B5L+bd8Aq/dX2UKGgGR8BYGoA4n4O+aAdNDgJoCEdAeXHMuvllsnV9lChoBkdAVHO4Ajps42gHTZsDaAhHQHnDyjxkNF11fZQoaAZHQF3LlkpZwGZoB00EA2gIR0B5199/jKgadX2UKGgGR0BmeWkcjqwAaAdNDwNoCEdAehq+j/MnqnV9lChoBkfASuNIEr5IpmgHTVACaAhHQHpbSJoCdSV1fZQoaAZHQGmaKWTot+VoB01aAmgIR0B6aspjMFEBdX2UKGgGR8BTMVkc0cfeaAdNKwJoCEdAeq7ESdvsJXV9lChoBkdAXMUnTiKiwmgHTYQCaAhHQHrECuuA7Pp1fZQoaAZHQGWFJeNT989oB03uAmgIR0B7DDMkhRqHdX2UKGgGR0BhR7PhQ3xXaAdNIgNoCEdAe1IXNke6qnV9lChoBkdAZqGn4O+ZgGgHTbYCaAhHQHuUViBoVVR1fZQoaAZHQGFevQnhKlJoB02GAmgIR0B7o43juKGddX2UKGgGR0BlJflfZ26kaAdNrgJoCEdAe+cd/8VHnXV9lChoBkdAZcugSOBDomgHTSgCaAhHQHv08dcSoOx1fZQoaAZHwEdJfvWpZOloB00mAmgIR0B8NfIhhYvGdWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 2940, "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:": "gAWV9wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 1024, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}", "__doc__": "\n    Rollout buffer used in on-policy algorithms like A2C/PPO.\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to classic advantage when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ", "__init__": "<function RolloutBuffer.__init__ at 0x7f5f538bc9d0>", "reset": "<function RolloutBuffer.reset at 0x7f5f538bca60>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7f5f538bcaf0>", "add": "<function RolloutBuffer.add at 0x7f5f538bcb80>", "get": "<function RolloutBuffer.get at 0x7f5f538bcc10>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7f5f538bcca0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f5f538b7f80>"}, "rollout_buffer_kwargs": {}, "batch_size": 34, "n_epochs": 30, "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:": "gAWVuQMAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLA0sTQwx0AIgAfACDAYMBUwCUToWUjAVmbG9hdJSFlIwScHJvZ3Jlc3NfcmVtYWluaW5nlIWUjF4vaG9tZS9nYWIvYW5hY29uZGEzL2VudnMvaHVnZ2luZy9saWIvcHl0aG9uMy45L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwIPGxhbWJkYT6US2FDAJSMDnZhbHVlX3NjaGVkdWxllIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMXi9ob21lL2dhYi9hbmFjb25kYTMvZW52cy9odWdnaW5nL2xpYi9weXRob24zLjkvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpRoAIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaCF9lH2UKGgYjAg8bGFtYmRhPpSMDF9fcXVhbG5hbWVfX5SMIWdldF9zY2hlZHVsZV9mbi48bG9jYWxzPi48bGFtYmRhPpSMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBmMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RoAihoByhLAUsASwBLAUsBSxNDBIgAUwCUaAkpjAFflIWUaA6MBGZ1bmOUS4VDAgABlIwDdmFslIWUKXSUUpRoFU5OaB0pUpSFlHSUUpRoI2g+fZR9lChoGIwEZnVuY5RoJ4wZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5RoKX2UaCtOaCxOaC1oGWguTmgvaDFHPxo24uscQy2FlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMIWUUpSFlGhHXZRoSX2UdYaUhlIwLg=="}, "system_info": {"OS": "Linux-5.15.0-122-generic-x86_64-with-glibc2.31 # 132~20.04.1-Ubuntu SMP Fri Aug 30 15:50:07 UTC 2024", "Python": "3.9.20", "Stable-Baselines3": "2.3.2", "PyTorch": "2.4.1+cu121", "GPU Enabled": "True", "Numpy": "1.24.4", "Cloudpickle": "3.1.0", "Gymnasium": "0.28.1"}}
+{"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 0x7f911441c9d0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f911441ca60>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f911441caf0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f911441cb80>", "_build": "<function ActorCriticPolicy._build at 0x7f911441cc10>", "forward": "<function ActorCriticPolicy.forward at 0x7f911441cca0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f911441cd30>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f911441cdc0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f911441ce50>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f911441cee0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f911441cf70>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f9114421040>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f911441e940>"}, "verbose": 2, "policy_kwargs": {}, "num_timesteps": 10240, "_total_timesteps": 10000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1728981878004589149, "learning_rate": 0.0008, "tensorboard_log": null, "_last_obs": null, "_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": -0.02400000000000002, "_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": 300, "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:": "gAWV9wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "n_steps": 1024, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwNUm9sbG91dEJ1ZmZlcpSTlC4=", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'advantages': <class 'numpy.ndarray'>, 'returns': <class 'numpy.ndarray'>, 'episode_starts': <class 'numpy.ndarray'>, 'log_probs': <class 'numpy.ndarray'>, 'values': <class 'numpy.ndarray'>}", "__doc__": "\n    Rollout buffer used in on-policy algorithms like A2C/PPO.\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to classic advantage when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ", "__init__": "<function RolloutBuffer.__init__ at 0x7f9114730a60>", "reset": "<function RolloutBuffer.reset at 0x7f9114730af0>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7f9114730b80>", "add": "<function RolloutBuffer.add at 0x7f9114730c10>", "get": "<function RolloutBuffer.get at 0x7f9114730ca0>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7f9114730d30>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f911472cdc0>"}, "rollout_buffer_kwargs": {}, "batch_size": 96, "n_epochs": 30, "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-5.15.0-122-generic-x86_64-with-glibc2.31 # 132~20.04.1-Ubuntu SMP Fri Aug 30 15:50:07 UTC 2024", "Python": "3.9.20", "Stable-Baselines3": "2.3.2", "PyTorch": "2.4.1+cu121", "GPU Enabled": "True", "Numpy": "1.24.4", "Cloudpickle": "3.1.0", "Gymnasium": "0.28.1"}}

results.json

@@ -1 +1 @@
-{"mean_reward": 4.449788357621813, "std_reward": 126.58686565638064, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-15T10:35:03.856601"}
+{"mean_reward": -736.5676308713504, "std_reward": 243.59139573870098, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-15T10:45:03.463674"}