My trained model

PPO_model_v1.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53d46ad769ef6d71e5723e94f419474629946eaa87a9ba4978cacdf3f5f0bd81
-size 141006
+oid sha256:9e343af67173387959be0b61a3a198a3a1d1e0700130a1f6c39575e2ed7917ef
+size 141863

PPO_model_v1/data

@@ -4,51 +4,54 @@
         ":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 0x16be3ce00>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x16be3cea0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x16be3cf40>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x16be3cfe0>",
-        "_build": "<function ActorCriticPolicy._build at 0x16be3d080>",
-        "forward": "<function ActorCriticPolicy.forward at 0x16be3d120>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x16be3d1c0>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x16be3d260>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x16be3d300>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x16be3d3a0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x16be3d440>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x16be3d4e0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x326075580>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x326075620>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x3260756c0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x326075760>",
+        "_build": "<function ActorCriticPolicy._build at 0x326075800>",
+        "forward": "<function ActorCriticPolicy.forward at 0x3260758a0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x326075940>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x3260759e0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x326075a80>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x326075b20>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x326075bc0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x326075c60>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x16b495440>"
+        "_abc_impl": "<_abc._abc_data object at 0x326078040>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 98304,
-    "_total_timesteps": 90000,
-    "_num_timesteps_at_start": 0,
+    "num_timesteps": 163840,
+    "_total_timesteps": 141072,
+    "_num_timesteps_at_start": 131072,
     "seed": null,
     "action_noise": null,
-    "start_time": 1705033899301809000,
+    "start_time": 1713851886945591000,
     "learning_rate": 0.0003,
     "tensorboard_log": null,
-    "_last_obs": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVkwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksghZSMAUOUdJRSlC4="
     },
     "_last_original_obs": null,
     "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.09226666666666672,
+    "_current_progress_remaining": -0.16139276397867763,
     "_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": 36,
+    "_n_updates": 20,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "gAWVFgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWBAAAAAAAAAABAQEBlGgIjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKUjA1ib3VuZGVkX2Fib3ZllGgRKJYEAAAAAAAAAAEBAQGUaBVLBIWUaBl0lFKUjAZfc2hhcGWUSwSFlIwDbG93lGgRKJYQAAAAAAAAAJqZmcD//3//UHfWvv//f/+UaAtLBIWUaBl0lFKUjARoaWdolGgRKJYQAAAAAAAAAJqZmUD//39/UHfWPv//f3+UaAtLBIWUaBl0lFKUjAhsb3dfcmVwcpSMPVstNC44MDAwMDAyZSswMCAtMy40MDI4MjM1ZSszOCAtNC4xODg3OTAzZS0wMSAtMy40MDI4MjM1ZSszOF2UjAloaWdoX3JlcHKUjDlbNC44MDAwMDAyZSswMCAzLjQwMjgyMzVlKzM4IDQuMTg4NzkwM2UtMDEgMy40MDI4MjM1ZSszOF2UjApfbnBfcmFuZG9tlE51Yi4=",
@@ -66,14 +69,14 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAgAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAgAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
         "n": "2",
         "start": "0",
         "_shape": [],
         "dtype": "int64",
         "_np_random": null
     },
-    "n_envs": 16,
+    "n_envs": 32,
     "n_steps": 1024,
     "gamma": 0.999,
     "gae_lambda": 0.98,
@@ -86,14 +89,14 @@
         "__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 0x16ba63240>",
-        "reset": "<function RolloutBuffer.reset at 0x16ba632e0>",
-        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x16ba63380>",
-        "add": "<function RolloutBuffer.add at 0x16ba634c0>",
-        "get": "<function RolloutBuffer.get at 0x16ba63560>",
-        "_get_samples": "<function RolloutBuffer._get_samples at 0x16ba63600>",
+        "__init__": "<function RolloutBuffer.__init__ at 0x325eb9760>",
+        "reset": "<function RolloutBuffer.reset at 0x325eb9800>",
+        "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x325eb98a0>",
+        "add": "<function RolloutBuffer.add at 0x325eb99e0>",
+        "get": "<function RolloutBuffer.get at 0x325eb9a80>",
+        "_get_samples": "<function RolloutBuffer._get_samples at 0x325eb9b20>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x16ba6c3c0>"
+        "_abc_impl": "<_abc._abc_data object at 0x325ea6c80>"
     },
     "rollout_buffer_kwargs": {},
     "batch_size": 64,

PPO_model_v1/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c543d98d10a7423065009166c90fca9844d54d99203126331277c68cc54ab93e
+oid sha256:7b3b6a07c3045223899a4b0ad809a9b8af23f3e517eefef270f8477e8ed5be3b
 size 82858

PPO_model_v1/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b8e78c23e2c861f27cf5406458d7d44aa05fa6d2923f582dfa5e63a47755d81
+oid sha256:1a4aded65acc1d676389bc3bc4dfba91348b3d2307d141d984b2021e83a3c251
 size 41074

PPO_model_v1/system_info.txt

@@ -1,8 +1,9 @@
-- OS: macOS-13.4.1-arm64-i386-64bit Darwin Kernel Version 22.5.0: Thu Jun  8 22:22:20 PDT 2023; root:xnu-8796.121.3~7/RELEASE_ARM64_T6000
+- OS: macOS-14.4.1-arm64-i386-64bit Darwin Kernel Version 23.4.0: Fri Mar 15 00:10:42 PDT 2024; root:xnu-10063.101.17~1/RELEASE_ARM64_T6000
 - Python: 3.11.3
 - Stable-Baselines3: 2.2.1
-- PyTorch: 2.1.2
+- PyTorch: 2.2.2
 - GPU Enabled: False
 - Numpy: 1.26.3
 - Cloudpickle: 3.0.0
 - Gymnasium: 0.29.1
+- OpenAI Gym: 0.26.2

README.md

@@ -16,7 +16,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 500.00 +/- 0.00
+      value: 476.60 +/- 49.07
       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 0x16be3ce00>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x16be3cea0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x16be3cf40>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x16be3cfe0>", "_build": "<function ActorCriticPolicy._build at 0x16be3d080>", "forward": "<function ActorCriticPolicy.forward at 0x16be3d120>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x16be3d1c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x16be3d260>", "_predict": "<function ActorCriticPolicy._predict at 0x16be3d300>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x16be3d3a0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x16be3d440>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x16be3d4e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x16b495440>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 98304, "_total_timesteps": 90000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1705033899301809000, "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": -0.09226666666666672, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVPAwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQHogAAAAAACMAWyUTaIBjAF0lEdASwixxDLKWHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQEsIrGR3eN11fZQoaAZHQHpwAAAAAABoB02nAWgIR0BLCRmkFfRedX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdASwo7JW/8EXV9lChoBkdAeaAAAAAAAGgHTZoBaAhHQEsKHrQgLZ11fZQoaAZHQHbwAAAAAABoB01vAWgIR0BLC8hcJMQFdX2UKGgGR0B+oAAAAAAAaAdN6gFoCEdASw0qhDgIhXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQEsNLpRoAXF1fZQoaAZHQHKQAAAAAABoB00pAWgIR0BLDeTmnwXqdX2UKGgGR0B2kAAAAAAAaAdNaQFoCEdASw3Uaya/h3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQEsOZ5Rjz7N1fZQoaAZHQHHgAAAAAABoB00eAWgIR0BLDiZfD1oQdX2UKGgGR0B1AAAAAAAAaAdNUAFoCEdASw+uTzND+nV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQEsQnrIHTql1fZQoaAZHQH9AAAAAAABoB030AWgIR0BLEVU2kzoEdX2UKGgGR0BxEAAAAAAAaAdNEQFoCEdASxKQeV9nb3V9lChoBkdAeQAAAAAAAGgHTZABaAhHQEsT3M6ij+J1fZQoaAZHQG0gAAAAAABoB0vpaAhHQEsURoRIz311fZQoaAZHQGyAAAAAAABoB0vkaAhHQEsU176YVqN1fZQoaAZHQHgQAAAAAABoB02BAWgIR0BLFNbkfcN6dX2UKGgGR0B5kAAAAAAAaAdNmQFoCEdASxUsQNCqqHV9lChoBkdAdVAAAAAAAGgHTVUBaAhHQEsWMOwxFiN1fZQoaAZHQGbAAAAAAABoB0u2aAhHQEsW4b0e2eB1fZQoaAZHQH9AAAAAAABoB030AWgIR0BLF+yquKXOdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdASxlbkfcN6XV9lChoBkdAd2AAAAAAAGgHTXYBaAhHQEsZO0LMLWt1fZQoaAZHQGtAAAAAAABoB0vaaAhHQEsag7o0Q9R1fZQoaAZHQHCgAAAAAABoB00KAWgIR0BLHGHpKSPmdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdASxxs41gpjXV9lChoBkdAfYAAAAAAAGgHTdgBaAhHQEsciGFi8Wd1fZQoaAZHQHGgAAAAAABoB00aAWgIR0BLHW7voePrdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdASx2lj3Ehq3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQEueDPGACnx1fZQoaAZHQH9AAAAAAABoB030AWgIR0BLnwoCuEEldX2UKGgGR0B+8AAAAAAAaAdN7wFoCEdAS6DUmUnogXV9lChoBkdAfZAAAAAAAGgHTdkBaAhHQEuiwevIOpd1fZQoaAZHQH9AAAAAAABoB030AWgIR0BLo0gbIcR2dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAS6SjUNKAa3V9lChoBkdAd+AAAAAAAGgHTX4BaAhHQEukOe8PFvR1fZQoaAZHQH9AAAAAAABoB030AWgIR0BLpVdX1anrdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAS6ZntfG+9XV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQEunuAqd6LR1fZQoaAZHQH9AAAAAAABoB030AWgIR0BLqP/io86ndX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAS6rgwXZXdXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQEuq7g88s+V1fZQoaAZHQH9AAAAAAABoB030AWgIR0BLqwiA2AG0dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAS6vy3CsOonV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQEusK5TZQHl1fZQoaAZHQH9AAAAAAABoB030AWgIR0BLrXJgb6xgdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAS65kmQbMo3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQEuwJ3PiT+x1fZQoaAZHQHhAAAAAAABoB02EAWgIR0BLsBrWRRuTdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAS7IVqN6w+3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQEuylme18b91fZQoaAZHQH9AAAAAAABoB030AWgIR0BLs+sxO+IudX2UKGgGR0BqIAAAAAAAaAdL0WgIR0BLs8tPHktFdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAS7SeGwiaAnV9lChoBkdAb0AAAAAAAGgHS/poCEdAS7X3Hq/ucHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQEu1pLVWjoJ1fZQoaAZHQH9AAAAAAABoB030AWgIR0BLtvE87p3YdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAS7g3BHkLhXV9lChoBkdAY2AAAAAAAGgHS5toCEdAS7h+hGpdbHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQEu6FaB7NSt1fZQoaAZHQH4wAAAAAABoB03jAWgIR0BLuZ8rqdH2dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAS7o6+36RAHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQEu7IsAeaKF1fZQoaAZHQDUAAAAAAABoB0sVaAhHQEu64QSSNfh1fZQoaAZHQH9AAAAAAABoB030AWgIR0BLu1tfoicHdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdATD41cdHUdHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQEw+LYPGyX51fZQoaAZHQH9AAAAAAABoB030AWgIR0BMQDjBEa2ndX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdATEC7PIGQjnV9lChoBkdAe/AAAAAAAGgHTb8BaAhHQExBKMefZmJ1fZQoaAZHQH9AAAAAAABoB030AWgIR0BMQhbW3BpIdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdATEQhUzbeuXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQExD0J4SpR51fZQoaAZHQH9AAAAAAABoB030AWgIR0BMRSjxkNF0dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdATEZz7uUliXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQExGuwHJLdx1fZQoaAZHQH9AAAAAAABoB030AWgIR0BMSFnRLK3edX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdATEfkgfU4JnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQExJa1TisGR1fZQoaAZHQH9AAAAAAABoB030AWgIR0BMSSowVTJhdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdATEmmrKeTV3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQExNvDP4VRF1fZQoaAZHQH9AAAAAAABoB030AWgIR0BMTbj94u9OdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdATE+4TbnHN3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQExQOT7l7t11fZQoaAZHQH9AAAAAAABoB030AWgIR0BMUKY7aIvbdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdATFGM6zVtoHV9lChoBkdAcLAAAAAAAGgHTQsBaAhHQExR5nlGPPt1fZQoaAZHQH9AAAAAAABoB030AWgIR0BMU5LytmthdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdATFNBMSK3u3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQExUixFAmiR1fZQoaAZHQH9AAAAAAABoB030AWgIR0BMVc+iaiK0dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdATFYU8FINE3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQExXqubI91V1fZQoaAZHQH9AAAAAAABoB030AWgIR0BMVzRYzSCwdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdATFizAvcrRXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQExYcJ+lTFV1ZS4="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 36, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True]", "bounded_above": "[ True  True  True  True]", "_shape": [4], "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "low_repr": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high_repr": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV/QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAgAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": "2", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "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 0x16ba63240>", "reset": "<function RolloutBuffer.reset at 0x16ba632e0>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x16ba63380>", "add": "<function RolloutBuffer.add at 0x16ba634c0>", "get": "<function RolloutBuffer.get at 0x16ba63560>", "_get_samples": "<function RolloutBuffer._get_samples at 0x16ba63600>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x16ba6c3c0>"}, "rollout_buffer_kwargs": {}, "batch_size": 64, "n_epochs": 4, "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": "macOS-13.4.1-arm64-i386-64bit Darwin Kernel Version 22.5.0: Thu Jun  8 22:22:20 PDT 2023; root:xnu-8796.121.3~7/RELEASE_ARM64_T6000", "Python": "3.11.3", "Stable-Baselines3": "2.2.1", "PyTorch": "2.1.2", "GPU Enabled": "False", "Numpy": "1.26.3", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1"}}
+{"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 0x326075580>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x326075620>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x3260756c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x326075760>", "_build": "<function ActorCriticPolicy._build at 0x326075800>", "forward": "<function ActorCriticPolicy.forward at 0x3260758a0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x326075940>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x3260759e0>", "_predict": "<function ActorCriticPolicy._predict at 0x326075a80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x326075b20>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x326075bc0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x326075c60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x326078040>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 163840, "_total_timesteps": 141072, "_num_timesteps_at_start": 131072, "seed": null, "action_noise": null, "start_time": 1713851886945591000, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAANDgFT4Pbdo+to0zvOTx0L6zOLU8iZcPvIGRmrx/FYi92jZlPhrYtj5doj072cGQPga+Ib/VzUC/YpgTPaEU9DzzU7c+WbkzPw6SSL0+pp+9ORn6PyeyXT/y3gQ+U5/qvV5xOj+51Ak/NuNPPYndED3UpAQ9b4UJvLpYnL0IjJG9eWb+Pm5moj5yNyU9XJqBPlEzir0SHHe+TbSjPMKfaj4O5eO+yIc9vzdWIT2rNkQ8Be66vCUXxD7lQSG9UMAhv+bZIz/oSRU/rCAZvU/Zpr4izjK+TOAUv1Qsar2+cAa9Bx/jPnfBaz8RFpo9aYMtvNvrFj6EvAQ/837dOwLz3L6cnhG+efMwv6Md/Lws9QA+sFLbPO3+SzwoTGy8epVKvQ0jsL7OWrq+uvkGvvHth76FiQJAJJGGP+RwVTzpvtg9i+V8vsRMQL9hIv+8V6QCP/DFcL0hmQu/7vlUPQAbsT447u49Z0sXv0pYKD49XaU//VhPOrLXpLs9pBe9U3elvhEBt76xSM8+903ePGiker4Q6KU99gkDv5W7q71Eypg+mER4PTrNyD4Fmh6919d8voVwAb9fxDM+vBHWvL9Pa750lWE/GqOjPgavSj1QWz0+140lvxwaNjzxZIy9QLVbPpMejr7miGY+BsWJPB20Q74j3sk/ZhOLP37M+LpydIA+lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksgSwSGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVkwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksghZSMAUOUdJRSlC4="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.16139276397867763, "_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": 20, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True]", "bounded_above": "[ True  True  True  True]", "_shape": [4], "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "low_repr": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high_repr": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAgAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "2", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 32, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "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 0x325eb9760>", "reset": "<function RolloutBuffer.reset at 0x325eb9800>", "compute_returns_and_advantage": "<function RolloutBuffer.compute_returns_and_advantage at 0x325eb98a0>", "add": "<function RolloutBuffer.add at 0x325eb99e0>", "get": "<function RolloutBuffer.get at 0x325eb9a80>", "_get_samples": "<function RolloutBuffer._get_samples at 0x325eb9b20>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x325ea6c80>"}, "rollout_buffer_kwargs": {}, "batch_size": 64, "n_epochs": 4, "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": "macOS-14.4.1-arm64-i386-64bit Darwin Kernel Version 23.4.0: Fri Mar 15 00:10:42 PDT 2024; root:xnu-10063.101.17~1/RELEASE_ARM64_T6000", "Python": "3.11.3", "Stable-Baselines3": "2.2.1", "PyTorch": "2.2.2", "GPU Enabled": "False", "Numpy": "1.26.3", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1", "OpenAI Gym": "0.26.2"}}

results.json

@@ -1 +1 @@
-{"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-19T12:54:36.797195"}
+{"mean_reward": 476.6, "std_reward": 49.0717841534216, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-23T11:51:58.540455"}