Upload PPO LunarLander-v2 trained agent

PPO-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:754fb3f67c78bddf7e30140e9bc342995e0b652c7b67d04e1e14755286252818
-size 150789
+oid sha256:f8482e614981ad728fbdd29682a7c1a0afa8a2622e4dedeec034820f76a267ae
+size 150784

PPO-LunarLander-v2/data

@@ -4,51 +4,51 @@
         ":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 0x7f6edc7b1550>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6edc7b15e0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6edc7b1670>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6edc7b1700>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f6edc7b1790>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f6edc7b1820>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f6edc7b18b0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6edc7b1940>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f6edc7b19d0>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6edc7b1a60>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6edc7b1af0>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6edc7b1b80>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7faa38081550>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7faa380815e0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7faa38081670>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7faa38081700>",
+        "_build": "<function ActorCriticPolicy._build at 0x7faa38081790>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7faa38081820>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7faa380818b0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7faa38081940>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7faa380819d0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7faa38081a60>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7faa38081af0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7faa38081b80>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f6edc7b0d40>"
+        "_abc_impl": "<_abc._abc_data object at 0x7faa38083900>"
     },
     "verbose": 2,
     "policy_kwargs": {},
-    "num_timesteps": 500736,
-    "_total_timesteps": 500000,
+    "num_timesteps": 1000448,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1728932104816668002,
+    "start_time": 1728935575455700893,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
     "_last_obs": null,
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
     },
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.0014719999999999178,
+    "_current_progress_remaining": -0.00044800000000000395,
     "_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": 14670,
+    "_n_updates": 29310,
     "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 0x7f6edcab45e0>",
-        "reset": "<function RolloutBuffer.reset at 0x7f6edcab4670>",
-        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7f6edcab4700>",
-        "add": "<function RolloutBuffer.add at 0x7f6edcab4790>",
-        "get": "<function RolloutBuffer.get at 0x7f6edcab4820>",
-        "_get_samples": "<function RolloutBuffer._get_samples at 0x7f6edcab48b0>",
+        "__init__": "<function RolloutBuffer.__init__ at 0x7faa383855e0>",
+        "reset": "<function RolloutBuffer.reset at 0x7faa38385670>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7faa38385700>",
+        "add": "<function RolloutBuffer.add at 0x7faa38385790>",
+        "get": "<function RolloutBuffer.get at 0x7faa38385820>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x7faa383858b0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f6edcaaefc0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7faa38386900>"
     },
     "rollout_buffer_kwargs": {},
-    "batch_size": 16,
+    "batch_size": 40,
     "n_epochs": 30,
     "clip_range": {
         ":type:": "<class 'function'>",

PPO-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a16d3b94c78fe19115860cb8965d6108071b38e7e2521fd1994f3d412931066
+oid sha256:878e578497a9e910bb713b330881e40dc19989facba9cd8307543c774798a443
 size 88490

PPO-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dccaeb3dfc5e4b0738c90ac41acee13f3e4ec4f7d524b0275d93c5d2040d1c4
+oid sha256:624272a4f20247c14f46620cee7127008fb14b2998f1782f90f9f0eb4c031de9
 size 43762

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 96.32 +/- 176.88
+      value: 218.64 +/- 35.05
       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 0x7f6edc7b1550>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f6edc7b15e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f6edc7b1670>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f6edc7b1700>", "_build": "<function ActorCriticPolicy._build at 0x7f6edc7b1790>", "forward": "<function ActorCriticPolicy.forward at 0x7f6edc7b1820>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f6edc7b18b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f6edc7b1940>", "_predict": "<function ActorCriticPolicy._predict at 0x7f6edc7b19d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f6edc7b1a60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f6edc7b1af0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f6edc7b1b80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f6edc7b0d40>"}, "verbose": 2, "policy_kwargs": {}, "num_timesteps": 500736, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1728932104816668002, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_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:": "gAWVQQwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwEQEF/QSi/SMAWyUTegDjAF0lEdApdXlr6+FlHV9lChoBkfAQR4LE1l5GGgHTegDaAhHQKXjkFwDNhV1fZQoaAZHwEYkVWS2Yv5oB03oA2gIR0Cl8MuWrwOOdX2UKGgGR8BDrpfYzzmPaAdN6ANoCEdApf3oSBbwB3V9lChoBkfAOxGt+1Bt12gHTegDaAhHQKYLh0yP+4t1fZQoaAZHQGjr/giu+ytoB00fAmgIR0CmF5bnX/YKdX2UKGgGR0BkmMrmQr+YaAdN7gJoCEdApiPU0zj3mHV9lChoBkdAVunrUsnRcGgHTegDaAhHQKYxDjPOY6Z1fZQoaAZHQEf62LHdXT5oB03oA2gIR0CmM4b+kxh2dX2UKGgGR0Bu6MW/JvHcaAdNRQFoCEdApj8IuqWC3HV9lChoBkdAYKCP7N0NjWgHTcYDaAhHQKZMxEcbR4R1fZQoaAZHQGtmpsoDxLFoB02dAWgIR0CmTbUrsjVydX2UKGgGR0Bqjgfp2U0OaAdN0QNoCEdAplsh0yP+43V9lChoBkfAOVyUxEfDDWgHTegDaAhHQKZol08vEjx1fZQoaAZHQGsmCqQzUI9oB02HAWgIR0CmaWO/UONHdX2UKGgGR0BcAGC7K7qZaAdN6ANoCEdApnZaJsO5KHV9lChoBkdAbJmAH3UQTWgHTTECaAhHQKaCVP5YYBN1fZQoaAZHQDLopvxYq5NoB03oA2gIR0CmkEGk30f6dX2UKGgGR0AGndqL0jC6aAdN6ANoCEdApp3/tv4ub3V9lChoBkdAbWGGgSOBD2gHTWcBaAhHQKaeq98qnWJ1fZQoaAZHQErd3JPqLTBoB03oA2gIR0Cmq6bI1cdHdX2UKGgGR0BNJQOvt+kQaAdN6ANoCEdAprimfEn9enV9lChoBkdAa7WMVk+X7mgHTbUBaAhHQKbD0aef7Jp1fZQoaAZHQG0G5JkGzKNoB00hAWgIR0CmxFGbCrLhdX2UKGgGR0BRsZg9eQdTaAdN6ANoCEdAptFGALApKHV9lChoBkdAacc1Aqur62gHTVECaAhHQKbdBjMmnfl1fZQoaAZHwC82yxA0KqpoB03oA2gIR0Cm32lnyup0dX2UKGgGR8AfTRArxy4naAdN6ANoCEdApu1wVwgkknV9lChoBkdAY/1zXBguy2gHTewBaAhHQKb5C7e2uxN1fZQoaAZHQCDxQ1rIo3JoB03oA2gIR0CnBprR8c+8dX2UKGgGR0BfxDXSSeRQaAdN6ANoCEdApxPGjsUqQXV9lChoBkdAcDsf4yoGZGgHTZkCaAhHQKcf6/vfCQ91fZQoaAZHwEwHoVVPva1oB03oA2gIR0CnLcfUe+23dX2UKGgGR0BvCyU1Q66raAdNKwNoCEdApy+GjO9nLHV9lChoBkdAaIeRPGhmG2gHTTsCaAhHQKc7Qrupjtp1fZQoaAZHQG0qNm16Vt5oB00ZAWgIR0CnO8E0zj3mdX2UKGgGR8A40+hXbM5faAdN6ANoCEdAp0kUIC2c8XV9lChoBkfAOoLELpiZv2gHTegDaAhHQKdWE1ivxH51fZQoaAZHQGq756dDpkhoB00NA2gIR0CnYwYqgAZLdX2UKGgGR8BFg/iPyTY/aAdN6ANoCEdAp3BUB2fTTnV9lChoBkdAT7FfXwsoUmgHTegDaAhHQKd9/mZE2Hd1fZQoaAZHQGQegGbCrLhoB00kAmgIR0Cnfz5bILgGdX2UKGgGR0Bc8GNipeeGaAdN6ANoCEdAp4wkAxSHd3V9lChoBkfAPuD3M6ij+WgHTegDaAhHQKeZ+8J2MbZ1fZQoaAZHQGLbqp1ie/ZoB03oA2gIR0CnppMRxtHhdX2UKGgGR0BgGu0svqTsaAdN6ANoCEdAp7POfukUK3V9lChoBkdAYlsF/x2B8WgHTegDaAhHQKfBYLc9GI91fZQoaAZHwCX9vMr3CbdoB03oA2gIR0CnzzjohY/3dX2UKGgGR0BBE5ZB9kSVaAdL1WgIR0Cnz6e+23KCdX2UKGgGR0Bgz28VYZEVaAdN6ANoCEdAp90EnZ00WXV9lChoBkdAXqKN4qwyI2gHTegDaAhHQKfqPT/ACXB1fZQoaAZHQGSEXQ+lj3FoB00HA2gIR0Cn96i17Y03dX2UKGgGR0BhBLohY/3WaAdN6ANoCEdAqASwjD8+A3V9lChoBkdAVrICJXQtz2gHTegDaAhHQKgSY/1xsEd1fZQoaAZHQESLV/+bVjJoB03oA2gIR0CoH7EHMUypdX2UKGgGR8CCebIuGsV+aAdNcAFoCEdAqCBlcry1/nV9lChoBkdAWJLzlLeyiWgHTegDaAhHQKgtfIZIg/11fZQoaAZHQFLI19v0h/1oB03oA2gIR0CoOjWaDwpfdX2UKGgGR0BudkDKYAsDaAdNaAFoCEdAqEW9pudf9nV9lChoBkdAZjmiRnvlVGgHTQwCaAhHQKhG7o/zJ6p1fZQoaAZHwFCPPqcEvCdoB03oA2gIR0CoU+TxwyZbdX2UKGgGR0BvkYy/KyOaaAdNSwFoCEdAqF9yuQp4KXV9lChoBkdAUppSMtK7I2gHTegDaAhHQKhtCt5D7ZZ1fZQoaAZHQG6SmNipeeFoB00CAWgIR0CobYiLMs6JdX2UKGgGR0BnsjdrO7g9aAdNPgJoCEdAqG7SQDFId3V9lChoBkdAcJSiyY5T62gHTQYBaAhHQKh57k/bCaZ1fZQoaAZHQGsoLksBhhJoB007AWgIR0CoeocGs3hodX2UKGgGR0BvkEIw/PgOaAdNMAFoCEdAqHsjMFEApHV9lChoBkdAY+wtjCpFTmgHTU0DaAhHQKiH4A+6iCd1fZQoaAZHQGuuxXfZVXFoB02iAWgIR0CoiMBhx5s1dX2UKGgGR0BpnGxt52QoaAdN4QFoCEdAqJShacI7eXV9lChoBkdAEMN+so2GZmgHTegDaAhHQKiiKgaFVT91fZQoaAZHQA9E9+w1R+BoB03oA2gIR0Cor2r9uP3jdX2UKGgGR8Aj0JRfnfVJaAdN6ANoCEdAqLywZsKsuHV9lChoBkfAMdkmQbMot2gHS7loCEdAqL0HIuGsWHV9lChoBkdAadWg0TDfnGgHTVEBaAhHQKi9rF3IMjN1fZQoaAZHQGo+r/CIk7hoB03VAWgIR0CoyVfapPykdX2UKGgGR8BoLSFXaJyiaAdNeQJoCEdAqMrZ3X7LuHV9lChoBkdAXVruAqd6LWgHTegDaAhHQKjYLmp2ll91fZQoaAZHQGxjP9DQZ4xoB01WAWgIR0Co4/n6/IsAdX2UKGgGR0BsLYWWQfZFaAdNRgFoCEdAqOSoLux8lXV9lChoBkdAb0KlF+d9UmgHTZ0BaAhHQKjli9VWCEp1fZQoaAZHQEOGDvmYBvJoB03oA2gIR0Co8/3eN1hcdX2UKGgGR0BthMw8GLUDaAdNIwFoCEdAqP9JLEk0JnV9lChoBkdAbmP2gWac7WgHTTIBaAhHQKj/3S88La51fZQoaAZHwHGrf91loUVoB01VAmgIR0CpDBJi7TUidX2UKGgGR0BnugM8YAKfaAdNlgFoCEdAqQzrUNKAa3V9lChoBkdAYEFPnB+F12gHTegDaAhHQKkZrDVH4Gl1fZQoaAZHQHAzPY4ACGNoB01WAWgIR0CpGnPnSv1UdX2UKGgGR0BmPM/+sHSnaAdNKgNoCEdAqSema4MF2XV9lChoBkdAaoDFdcB2fWgHTUwBaAhHQKkoTyIYWLx1fZQoaAZHQHAdzifg75poB00rAWgIR0CpMxnAh0QsdX2UKGgGR0BkIopYs/Y8aAdNzwNoCEdAqT/1zXBgu3V9lChoBkdAalu28Zk08GgHTaEBaAhHQKlAum/nGKh1fZQoaAZHwDoBmI0qH45oB0uyaAhHQKlBBG3nZCh1fZQoaAZHQGkHd5prULFoB03pAmgIR0CpTTYA80UHdX2UKGgGR0AavAM2FWXDaAdN6ANoCEdAqVn1BOYYznV9lChoBkdAbl5FbVz6rWgHTQgBaAhHQKlaa3lS0jV1fZQoaAZHQGtbKIi1RchoB00vAmgIR0CpZmaG5+YudX2UKGgGR8BzDqDPGACoaAdNBwNoCEdAqWgW1D0Dl3VlLg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 14670, "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 0x7f6edcab45e0>", "reset": "<function RolloutBuffer.reset at 0x7f6edcab4670>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7f6edcab4700>", "add": "<function RolloutBuffer.add at 0x7f6edcab4790>", "get": "<function RolloutBuffer.get at 0x7f6edcab4820>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7f6edcab48b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f6edcaaefc0>"}, "rollout_buffer_kwargs": {}, "batch_size": 16, "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"}}
+{"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 0x7faa38081550>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7faa380815e0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7faa38081670>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7faa38081700>", "_build": "<function ActorCriticPolicy._build at 0x7faa38081790>", "forward": "<function ActorCriticPolicy.forward at 0x7faa38081820>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7faa380818b0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7faa38081940>", "_predict": "<function ActorCriticPolicy._predict at 0x7faa380819d0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7faa38081a60>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7faa38081af0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7faa38081b80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7faa38083900>"}, "verbose": 2, "policy_kwargs": {}, "num_timesteps": 1000448, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1728935575455700893, "learning_rate": 0.0003, "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": -0.00044800000000000395, "_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": 29310, "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 0x7faa383855e0>", "reset": "<function RolloutBuffer.reset at 0x7faa38385670>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x7faa38385700>", "add": "<function RolloutBuffer.add at 0x7faa38385790>", "get": "<function RolloutBuffer.get at 0x7faa38385820>", "_get_samples": "<function RolloutBuffer._get_samples at 0x7faa383858b0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7faa38386900>"}, "rollout_buffer_kwargs": {}, "batch_size": 40, "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": 96.31666565968186, "std_reward": 176.8810722072378, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-14T21:51:48.961888"}
+{"mean_reward": 218.63519564022636, "std_reward": 35.047890771302626, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-14T23:10:24.835506"}