Upload PPO LunarLander-v2 trained agent

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- LunarLander-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: 222.18 +/- 17.29
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **LunarLander-v2**
+This is a trained model of a **PPO** agent playing **LunarLander-v2**
+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 0x7f3c3a1b0160>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3c3a1b01f0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3c3a1b0280>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3c3a1b0310>", "_build": "<function ActorCriticPolicy._build at 0x7f3c3a1b03a0>", "forward": "<function ActorCriticPolicy.forward at 0x7f3c3a1b0430>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f3c3a1b04c0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3c3a1b0550>", "_predict": "<function ActorCriticPolicy._predict at 0x7f3c3a1b05e0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3c3a1b0670>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3c3a1b0700>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3c3a1b0790>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f3c3a19b940>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 507904, "_total_timesteps": 500000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1687766057229259886, "learning_rate": 0.0003, "tensorboard_log": null, "_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:": "gAWVPgwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHQGCI16Vt4zKMAWyUTegDjAF0lEdAp70m0PYnOXV9lChoBkdAXxhYGMXJo2gHTegDaAhHQKfBkDgZTAF1fZQoaAZHQFqgONo8IRhoB03oA2gIR0CnweKsdT5wdX2UKGgGR0BmeheLNwBHaAdNkQFoCEdAp8NKOvMbFXV9lChoBkdAZHlbuc+aB2gHTegDaAhHQKfDYO3lS0l1fZQoaAZHQFfpOQhfShJoB03oA2gIR0CnxIV/DtPYdX2UKGgGR0BcglVPva11aAdN6ANoCEdAp8WSs+3YtnV9lChoBkdAXaIYTCcf/2gHTegDaAhHQKfPPqY7aIx1fZQoaAZHQFO+Pppvgm9oB03oA2gIR0Cnz6ozvZyudX2UKGgGR0Bi5Gg+QlruaAdNxgFoCEdAp9GWbTc7AHV9lChoBkfAFyybhFVktmgHTUwBaAhHQKfSxSR8twt1fZQoaAZHQFoPKwpvxYtoB03oA2gIR0Cn2srSE12rdX2UKGgGR0BEpfffoA4oaAdNFAFoCEdAp94axs2vS3V9lChoBkdAXK+E4//vOWgHTegDaAhHQKfg4yGi5/d1fZQoaAZHQF/uVKf4AS5oB03oA2gIR0Cn4rKdYnv2dX2UKGgGR0Bg4g0sOG0vaAdN6ANoCEdAp+XbSRbKR3V9lChoBkdAXJkGB4D9wWgHTegDaAhHQKfqLkUbkwN1fZQoaAZHQGM+wlByCFtoB03oA2gIR0Cn636DwpfAdX2UKGgGR0BdCOFYdQwcaAdN6ANoCEdAp/XHIGQjlnV9lChoBkdAVMm7e2uxKWgHTegDaAhHQKf2RKQJXyR1fZQoaAZHQFr8zU7Sy+poB03oA2gIR0Cn+DQEyLyddX2UKGgGR0BfMf+bVjI8aAdN6ANoCEdAp/hNkvsZ53V9lChoBkdAY5gxTsIE82gHTegDaAhHQKf5bFzdUKl1fZQoaAZHQGCNbwSamXRoB03oA2gIR0Cn+ouMVDa5dX2UKGgGR0Bj6idOIqLCaAdN6ANoCEdAp/uBHd43WHV9lChoBkdAYiWSA6Mir2gHTegDaAhHQKf7z5mh/RV1fZQoaAZHQFzEyQxN7BxoB03oA2gIR0CoBolrVOKwdX2UKGgGR0ALvvOQhfShaAdNKgFoCEdAqAlLRplBhXV9lChoBkdASwqDCgsbvWgHS95oCEdAqAlc7QswtnV9lChoBkfAYqpjvNNahmgHTV8DaAhHQKgKT+nZTQ51fZQoaAZHP/9PbwjMV1xoB01FAWgIR0CoC8XjMmngdX2UKGgGR0BiB852hZhbaAdN6ANoCEdAqAyGrGR3eXV9lChoBkdATZVVBD5TImgHTRYBaAhHQKgN037UG3Z1fZQoaAZHQGOFirDIikhoB03oA2gIR0CoE2IoNNJwdX2UKGgGR7/m+NDMNc4YaAdL7mgIR0CoE88CxNZedX2UKGgGR0Biq52r4nF6aAdN6ANoCEdAqBWJbfP5YnV9lChoBkdAER5IpYs/ZGgHTQQBaAhHQKgYXbB42TB1fZQoaAZHQGA+sXSBshxoB03oA2gIR0CoGMHX/YJ3dX2UKGgGR0BhaX4dp7C0aAdN6ANoCEdAqByi3I+4b3V9lChoBkdAZW5Vsk6cRWgHTegDaAhHQKgd53L3bmF1fZQoaAZHQDVEahpQDV9oB01GAWgIR0CoH3nZ9NN8dX2UKGgGR0BWp8G1QZXNaAdN6ANoCEdAqCWLRSgoPXV9lChoBkdAYcibbUPQOWgHTegDaAhHQKgnIU1yeZp1fZQoaAZHQGMpE690zTFoB03oA2gIR0CoKamYjSogdX2UKGgGR0Bh52p84PwvaAdN6ANoCEdAqCtSTUy57XV9lChoBkdAT531QIldC2gHTegDaAhHQKg5SzfrKNh1fZQoaAZHQF0XPP9kz41oB03oA2gIR0CoPKCA+Y+jdX2UKGgGR0BcF87hegL7aAdN6ANoCEdAqD2w2OyVwHV9lChoBkdAYusF/x2B8WgHTegDaAhHQKg/WF/x2B91fZQoaAZHQFeJaiblRxdoB03oA2gIR0CoQRVwPy08dX2UKGgGR0BixTwjMV1waAdN6ANoCEdAqEXVcMVk+XV9lChoBkdAZGZ0+1SflWgHTegDaAhHQKhHQIAwPAh1fZQoaAZHQGGQ7IT4+KVoB03oA2gIR0CoSp876pHadX2UKGgGR0BhaEcfeUILaAdN6ANoCEdAqEs4rWiDd3V9lChoBkdAXP8FeOXE62gHTegDaAhHQKhRQGC7K7t1fZQoaAZHQF9L0vGp++doB03oA2gIR0CoUz4ku6ErdX2UKGgGR0Bi22UILPUsaAdN6ANoCEdAqFT54B3iaXV9lChoBkdAWww5bQkX12gHTegDaAhHQKhaxAprk811fZQoaAZHQGFY5yuIRAdoB03oA2gIR0CoXFkgOjIrdX2UKGgGR0BgLjaRISUUaAdN6ANoCEdAqF7CgK4QSXV9lChoBkdAaG1MAWBSUGgHTVABaAhHQKheyDFId2h1fZQoaAZHQGIa+3QUpNNoB03oA2gIR0CoYB4agmJFdX2UKGgGR0Bb+TNpudf+aAdN6ANoCEdAqGzW1F6RhnV9lChoBkdAWvspd8iOemgHTegDaAhHQKhxMvovBad1fZQoaAZHQFzB9oexOcloB03oA2gIR0Cock0FKTStdX2UKGgGR8AdmQfZElVtaAdL/GgIR0Coc6SdWhh6dX2UKGgGR0BjgLUI9kjHaAdN6ANoCEdAqHPra4+bE3V9lChoBkdAYNDA2ycCo2gHTegDaAhHQKh1kBd2Pkt1fZQoaAZHQGDckfT1CgNoB03oA2gIR0CoefvCdjG2dX2UKGgGR0BeZ8kUsWfsaAdN6ANoCEdAqHtdVrAP/nV9lChoBkdAJ+onBtUGV2gHS+toCEdAqHyJRKpT/HV9lChoBkdAWfRkJ8fFJmgHTegDaAhHQKh+LgYP5Hp1fZQoaAZHQFtS7OmixmloB03oA2gIR0CofpibUgB+dX2UKGgGR0BgXnv2GqPwaAdN6ANoCEdAqIQ6V4X403V9lChoBkdAXz6P/7zkIWgHTegDaAhHQKiGdxG2Cul1fZQoaAZHQFt/Zof0VahoB03oA2gIR0CojuTZxrBTdX2UKGgGR0BZkBN21UlzaAdN6ANoCEdAqJCaed07sHV9lChoBkdAYpLs2NvOyGgHTegDaAhHQKiS8goPTXt1fZQoaAZHQFw29ZA6dUdoB03oA2gIR0ColFuXNTtLdX2UKGgGR0BfW4TGo73gaAdN6ANoCEdAqJbDiEQGwHV9lChoBkdAYROGKQ7tA2gHTegDaAhHQKiiPIU8FIN1fZQoaAZHQGMxF5v99+hoB03oA2gIR0Cooy5lFtsOdX2UKGgGR0BAsYVARkEtaAdNHwFoCEdAqKNtXT3IuHV9lChoBkdAXXZRqGlANWgHTegDaAhHQKikp8Jlar51fZQoaAZHQGE6BQvYe1doB03oA2gIR0Copu1cdHUddX2UKGgGR0Bh3YzpHI6saAdN6ANoCEdAqKzi+cpb2XV9lChoBkdAYgmclw97nmgHTegDaAhHQKiucXDWK/F1fZQoaAZHQGECKgIyCWhoB03oA2gIR0Cor4OqWC2+dX2UKGgGR0Bg7jaIvalDaAdN6ANoCEdAqLD+2d/ax3V9lChoBkdAZEYQJ5VwP2gHTegDaAhHQKixY5MDfWN1fZQoaAZHQEEELJjlPrRoB0vUaAhHQKi0m/8EV351fZQoaAZHQGRVF8XvYvpoB03oA2gIR0CotucW0qpcdX2UKGgGR0BcRt70Fr2yaAdN6ANoCEdAqLiwjD8+A3V9lChoBkdAQ/XB7/n4f2gHTSUBaAhHQKi5Kp97Wup1fZQoaAZHwBikUCaJAMVoB0vmaAhHQKi54UPhAGB1fZQoaAZHQF15CN0eU6hoB03oA2gIR0Covg9bxEv1dX2UKGgGR0BkgwIfKZDzaAdN6ANoCEdAqMHxk/bCanV9lChoBkdAXQ/6hxo7FWgHTegDaAhHQKjD9ZDArQR1fZQoaAZHwBGdXgccU/RoB00eAWgIR0CoxE9WQwK0dX2UKGgGR0Ba4vACW/rTaAdN6ANoCEdAqMdTmnwXqXVlLg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 196, "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "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, "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": "Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

my_first_rl_agent.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dc57b06e57a1d71275601c661ed6d68cfbcc5c15b19b9887750af6bdd13e99b
+size 146749

my_first_rl_agent/_stable_baselines3_version

@@ -0,0 +1 @@
+2.0.0a5

my_first_rl_agent/data

@@ -0,0 +1,99 @@
+{
+    "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 0x7f3c3a1b0160>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f3c3a1b01f0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f3c3a1b0280>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f3c3a1b0310>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f3c3a1b03a0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f3c3a1b0430>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f3c3a1b04c0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f3c3a1b0550>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f3c3a1b05e0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f3c3a1b0670>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f3c3a1b0700>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f3c3a1b0790>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f3c3a19b940>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 507904,
+    "_total_timesteps": 500000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1687766057229259886,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_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": 196,
+    "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:": "gAWV1QAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCloCmgOjApfbnBfcmFuZG9tlE51Yi4=",
+        "n": "4",
+        "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,
+    "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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"
+    }
+}

my_first_rl_agent/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:977f731c6ab989c8783022ad98a46398cbb29343f088e314da47f9bd447eaf06
+size 87929

my_first_rl_agent/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:922f28269b7e1dde0c011f77f3e0b220cc3d78644e446cefcd98afb5a0f85e40
+size 43329

my_first_rl_agent/pytorch_variables.pth

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

my_first_rl_agent/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.107+-x86_64-with-glibc2.31 # 1 SMP Sat Apr 29 09:15:28 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.0.1+cu118
+- GPU Enabled: True
+- Numpy: 1.22.4
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

results.json

@@ -0,0 +1 @@
+{"mean_reward": 222.18496483373315, "std_reward": 17.294627005871153, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-06-26T08:51:57.743261"}