Upload PPO CartPole-v1 trained agent

PPO-CartPole-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11e460c543ad86e54a921be0bdd8bf95f69c41492a072334f6b69deb9346a846
+size 137871

PPO-CartPole-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+1.8.0

PPO-CartPole-v1/data

@@ -0,0 +1,96 @@
+{
+    "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 0x7faddffca9e0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7faddffcaa70>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7faddffcab00>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7faddffcab90>",
+        "_build": "<function ActorCriticPolicy._build at 0x7faddffcac20>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7faddffcacb0>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7faddffcad40>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7faddffcadd0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7faddffcae60>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7faddffcaef0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7faddffcaf80>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7faddffcb010>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7faddffc3240>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1682620674261997385,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.015808000000000044,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 310,
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_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]",
+        "bounded_below": "[ True  True  True  True]",
+        "bounded_above": "[ True  True  True  True]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLAowGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 2,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "n_steps": 2048,
+    "gamma": 0.99,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.0,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 10,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

PPO-CartPole-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01ab916456c79602ef27190da1eb565ff199ef213ceace3053c9871d14942101
+size 82809

PPO-CartPole-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0ec0cf0c90a6ba543c7e5f05c9997c1d9816365cd48fb7fb86c8e4891fa9d06
+size 40769

PPO-CartPole-v1/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

PPO-CartPole-v1/system_info.txt

@@ -0,0 +1,7 @@
+- OS: Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022
+- Python: 3.10.11
+- Stable-Baselines3: 1.8.0
+- PyTorch: 2.0.0+cu118
+- GPU Enabled: True
+- Numpy: 1.22.4
+- Gym: 0.21.0

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- CartPole-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+    metrics:
+    - type: mean_reward
+      value: 500.00 +/- 0.00
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **CartPole-v1**
+This is a trained model of a **PPO** agent playing **CartPole-v1**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+
+## Usage (with Stable-baselines3)
+TODO: Add your code
+
+
+```python
+from stable_baselines3 import ...
+from huggingface_sb3 import load_from_hub
+
+...
+```

config.json

@@ -0,0 +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 0x7faddffca9e0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7faddffcaa70>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7faddffcab00>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7faddffcab90>", "_build": "<function ActorCriticPolicy._build at 0x7faddffcac20>", "forward": "<function ActorCriticPolicy.forward at 0x7faddffcacb0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7faddffcad40>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7faddffcadd0>", "_predict": "<function ActorCriticPolicy._predict at 0x7faddffcae60>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7faddffcaef0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7faddffcaf80>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7faddffcb010>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7faddffc3240>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1015808, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1682620674261997385, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.015808000000000044, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVRAwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQH9AAAAAAACMAWyUTfQBjAF0lEdAiONLbpNbknV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQIjjgGMXJo11fZQoaAZHQH9AAAAAAABoB030AWgIR0CI5Aq5sj3VdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAiORlt0mtyXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQIjkzAUL2Ht1fZQoaAZHQH9AAAAAAABoB030AWgIR0CI5U/5ckdFdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAiOXw40dilXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQIjl5s/IKdB1fZQoaAZHQH9AAAAAAABoB030AWgIR0CI5l7k4m1IdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAiOcnwgDA8HV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQIjnuGmDUVl1fZQoaAZHQH9AAAAAAABoB030AWgIR0CI6EZNwiqydX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAiOhcM/hVEXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQIjoeyTpxFR1fZQoaAZHQH9AAAAAAABoB030AWgIR0CI6NBVMmF8dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAiOkWOQyRCHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQIjpQkVvddp1fZQoaAZHQH9AAAAAAABoB030AWgIR0CI6Xhm5DqodX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAiOoEvTPSlXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQIjqYCQtBfN1fZQoaAZHQH9AAAAAAABoB030AWgIR0CI6sUQCjk/dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAiOtPXK8tgHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQIjr+iL2pQ11fZQoaAZHQH9AAAAAAABoB030AWgIR0CI6/AIIF/ydX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAiOxi0v4/NnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQIjtJ0W/JvJ1fZQoaAZHQH9AAAAAAABoB030AWgIR0CI7bFG5MDfdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAiO47BO58SnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQIjuUqDsdDJ1fZQoaAZHQH9AAAAAAABoB030AWgIR0CI7nOX3QD3dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAiO7P7WNFSnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQIjvFo8IRiB1fZQoaAZHQH9AAAAAAABoB030AWgIR0CI70CNjslcdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAiO90rsjVx3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQIjv/CQ9zOp1fZQoaAZHQH9AAAAAAABoB030AWgIR0CJqrqqwQlKdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAiataL4vexnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQImsJDLKV6h1fZQoaAZHQH9AAAAAAABoB030AWgIR0CJrSLQ5WBCdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAia0a06YE4nV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQImtvBciW3V1fZQoaAZHQH9AAAAAAABoB030AWgIR0CJrpIHTqjadX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAia8eocaOxXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQImvsVvddmh1fZQoaAZHQH9AAAAAAABoB030AWgIR0CJr8dfb9IgdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAia/lXiiqQ3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQImwOQ4jrzJ1fZQoaAZHQH9AAAAAAABoB030AWgIR0CJsH0NjLB9dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAibCnjQzDXXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQImw7Q/oq1B1fZQoaAZHQH9AAAAAAABoB030AWgIR0CJsX3Qla8pdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAibHZooNNJ3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQImyRHy3CsR1fZQoaAZHQH9AAAAAAABoB030AWgIR0CJssjHGS6ldX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAibNuBtk4FXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQImzZAB1cMV1fZQoaAZHQH9AAAAAAABoB030AWgIR0CJs9s/IKc/dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAibSi4SYgJXV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQIm1MUM5OrR1fZQoaAZHQH9AAAAAAABoB030AWgIR0CJtbmdRR/FdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAibXOJDVpbnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQIm17BZZB9l1fZQoaAZHQH9AAAAAAABoB030AWgIR0CJtj7IkqtpdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAibaL3Cbc5HV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQIm2uIRAbAF1fZQoaAZHQH9AAAAAAABoB030AWgIR0CJtvGFzuF6dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAibeC6pYLcHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQIm34FLWZqp1fZQoaAZHQH9AAAAAAABoB030AWgIR0CJuE6wt8NQdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAibjmXXyy2XV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQIm5qfcvduZ1fZQoaAZHQH9AAAAAAABoB030AWgIR0CJuaCPp6hQdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAiboir1dxAHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQIm6+dRR/Ex1fZQoaAZHQH9AAAAAAABoB030AWgIR0CJu4qjJuEVdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAibwUEHMUy3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQIm8KUFB6a91fZQoaAZHQH9AAAAAAABoB030AWgIR0CJvEeBg/kedX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAibyZcLSeAnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQIm83KGL1mJ1fZQoaAZHQH9AAAAAAABoB030AWgIR0CJvQYGdI5HdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAib06uOjqOnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQIm9w75mAb11fZQoaAZHQH9AAAAAAABoB030AWgIR0CJvh18LKFJdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAib6NNrTH83V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQIm/F4A0bcZ1fZQoaAZHQH9AAAAAAABoB030AWgIR0CJv7/FzdULdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAib+1+I/JNnV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQInAMPWhAW11fZQoaAZHQH9AAAAAAABoB030AWgIR0CJwQh6By0bdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAicGmyPdVN3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQInCO9vjwQV1fZQoaAZHQH9AAAAAAABoB030AWgIR0CJwlHbypaSdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAicJwv6CUYHV9lChoBkdAf0AAAAAAAGgHTfQBaAhHQInCx1q33Ht1fZQoaAZHQH9AAAAAAABoB030AWgIR0CJww5ZKWcCdX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAicM6nrIHT3V9lChoBkdAf0AAAAAAAGgHTfQBaAhHQInDcXLvCuV1fZQoaAZHQH9AAAAAAABoB030AWgIR0CJw/kMCtA+dX2UKGgGR0B/QAAAAAAAaAdN9AFoCEdAicRSTQmeDnVlLg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 310, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_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]", "bounded_below": "[ True  True  True  True]", "bounded_above": "[ True  True  True  True]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLAowGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 2, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.31 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.10.11", "Stable-Baselines3": "1.8.0", "PyTorch": "2.0.0+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": 500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-27T18:53:09.424279"}