Upload LunarLander-v2 with A2C trained agent

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- LunarLander-v2
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: A2C
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: 47.81 +/- 135.90
+      name: mean_reward
+      verified: false
+---
+
+# **A2C** Agent playing **LunarLander-v2**
+This is a trained model of a **A2C** 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 0x79ef69a43880>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x79ef69a43920>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x79ef69a439c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x79ef69a43a60>", "_build": "<function ActorCriticPolicy._build at 0x79ef69a43b00>", "forward": "<function ActorCriticPolicy.forward at 0x79ef69a43ba0>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x79ef69a43c40>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x79ef69a43ce0>", "_predict": "<function ActorCriticPolicy._predict at 0x79ef69a43d80>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x79ef69a43e20>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x79ef69a43ec0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x79ef69a43f60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x79ef69b89b40>"}, "verbose": 0, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVlgAAAAAAAAB9lCiMCG5ldF9hcmNolF2UKE0AAU0AAWWMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", "net_arch": [256, 256], "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "num_timesteps": 1000064, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1749305287819857724, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdgEAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWAAEAAAAAAAAmISg+nLcIvGzEDTvMMcy4rNxvvewbL7oAAIA/AACAP0A1az54XKw8JdfSt9FmU7blTD4+mqYLNwAAgD8AAIA/c4YUPsEEgT8NmWA+USrcvmVrkzvCr5O8AAAAAAAAAAAttYc+H773PEI+mbrvlGi5m1mKPqbG3jkAAIA/AAAAANowID82Vqo+gI/tPmILx766pgk9E2oSvQAAAAAAAAAARWEtv4D3ST8jmMi+QpZMvpPGKb3Pj5Q8AAAAAAAAAAAzqZk9cz5qPx6p4D1Vz7++ek7lO9pznzwAAAAAAAAAACCQcD4oh1c/nZqRPu/6v74h6og8/muIOwAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksISwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVfAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAAAAAAAAAAAAJSMBW51bXB5lIwFZHR5cGWUk5SMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCIWUjAFDlHSUUpQu"}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -6.4000000000064e-05, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVFwwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwFI6piZv1lKMAWyUS7uMAXSUR0CX/hulGgBcdX2UKGgGR8BSuhaouPFOaAdLz2gIR0CX/nybx3FDdX2UKGgGR8BEKkETxoZiaAdL6WgIR0CX/r49X9zfdX2UKGgGR8BQ57lvIfbLaAdLhGgIR0CX/6N2ki2VdX2UKGgGR8BOKwSBbwBpaAdLt2gIR0CYAE9LHuJDdX2UKGgGR7/qX3xnWattaAdNBwFoCEdAmAHH7DVH4HV9lChoBkfAVjkDuBtk4GgHS+doCEdAmANA176YV3V9lChoBkfANCAfp2U0N2gHS+ZoCEdAmAZTFMqSYHV9lChoBkdAb0Uv+OwPiGgHTS4BaAhHQJgGZc7hegN1fZQoaAZHQGnowrlNlAhoB00HAWgIR0CYByGHYYixdX2UKGgGR8AwDuwosqaxaAdL7GgIR0CYCEj2zv7WdX2UKGgGR0BxY6Bz3h4uaAdNDgFoCEdAmAndNet0WHV9lChoBkfASFWsNlRP42gHTUwBaAhHQJgJ9tQ9A5d1fZQoaAZHwDmj62v0ROFoB00LAWgIR0CYDAunMt9QdX2UKGgGR0BuDfUjLSuyaAdNPwFoCEdAmAw2yTpxFXV9lChoBkfANPPz8P4EfWgHS+JoCEdAmAzEGFBY3nV9lChoBkdAb/a+TNdJKGgHTQIBaAhHQJgPBGlQ/HJ1fZQoaAZHwCZ9bmlqJuVoB0vkaAhHQJgPxg9eQdV1fZQoaAZHQGc2j+zdDY1oB01hAWgIR0CYEE8h9srNdX2UKGgGR8BTZO7+T/yYaAdLrmgIR0CYEN2ki2UjdX2UKGgGR0Bv0J3FDOTraAdNGQFoCEdAmBFVUMoc73V9lChoBkfAQgeYUnG83GgHS9FoCEdAmBKJPdl/Y3V9lChoBkfAS9jcRDkU9WgHS7xoCEdAmBR6esgdO3V9lChoBkfASUlXLeQ+2WgHS4ZoCEdAmBTol2NedHV9lChoBkdAaXgCbtqpLmgHTU0BaAhHQJgVgmw7kn11fZQoaAZHwFx4ydFvybxoB0v2aAhHQJgXIKmbb111fZQoaAZHQGq04rBj4HpoB01HAWgIR0CYGo11W8yvdX2UKGgGR0BtT2OuJUHZaAdNDwFoCEdAmBtkIToMa3V9lChoBkdAG2mXPZ7HAGgHS+VoCEdAmByIPK+zt3V9lChoBkdAa19JlrdnCmgHTR8BaAhHQJgeO8Fpwjt1fZQoaAZHwFXNK4hEBsBoB0vkaAhHQJgfI2ZRbbF1fZQoaAZHQGVf1QAMlTpoB02xAWgIR0CYH74VRDTjdX2UKGgGR8BQeQJPZZjhaAdLo2gIR0CYIFXtBv74dX2UKGgGR0BqJ0YuTRplaAdNUgFoCEdAmCEK99MK1HV9lChoBkfARAfanJkoW2gHS9xoCEdAmCLJsj3VTnV9lChoBkdAVJ+/gzguRWgHTegDaAhHQJgl5Lh73PB1fZQoaAZHwDkE5OrQw9JoB00gAWgIR0CYJhMQVbiZdX2UKGgGR8BNqV6E8JUpaAdLrmgIR0CYJo14gRsedX2UKGgGR8Ajw4Wk8A7xaAdNJQFoCEdAmChTYmLLp3V9lChoBkfAVzLGgi/wiWgHS7hoCEdAmCiGuDBdlnV9lChoBkdAcQke4TbnHWgHTSIBaAhHQJgovQnhKlJ1fZQoaAZHQGnMUrK/201oB00dAWgIR0CYKQiYb83udX2UKGgGR0BjTNlum78OaAdNeAFoCEdAmCmmACnxa3V9lChoBkfAVQWXa8Hv+mgHS4loCEdAmCm1bRneznV9lChoBkfAVAOjesPrfWgHS55oCEdAmCwCU1Q663V9lChoBkfAN5lxjriVB2gHTQQBaAhHQJgsLgzguRN1fZQoaAZHwFVtnuRcNYtoB0u4aAhHQJgsR8MNMGp1fZQoaAZHwE5DEn9ehPFoB0vWaAhHQJguo0uUUwl1fZQoaAZHwFvXMtsenydoB00LAWgIR0CYL0/Ho5ggdX2UKGgGR0BoVExXXAdoaAdNZwFoCEdAmDJk078vVXV9lChoBkdAa2JnAZbY9WgHTT8BaAhHQJgy1Fy7wrl1fZQoaAZHQGWD9gOSW7hoB02/AWgIR0CYM0q1PWQPdX2UKGgGR8BRF5Qk5ZKWaAdL32gIR0CYM5iXY150dX2UKGgGR8BQwXfMwDeTaAdL/2gIR0CYNME7nxJ/dX2UKGgGR8BN3TbWVeKLaAdLqWgIR0CYNbGz8gp0dX2UKGgGR8BR4tycTakAaAdNNAFoCEdAmDrA0Kqn33V9lChoBkfAYAolfJFLFmgHS8doCEdAmDtHxe9i+nV9lChoBkfAXsD8IiTt9mgHTQQBaAhHQJg9V4ptrKx1fZQoaAZHwETVqbjLjghoB00DAWgIR0CYPY6J66atdX2UKGgGR0Bqr4DYAbQ1aAdNRwFoCEdAmD8dRBNVR3V9lChoBkc/7xwwTM7lrGgHTQYBaAhHQJhAJayKNyZ1fZQoaAZHQGssOIRAbAFoB015AWgIR0CYQrymygPFdX2UKGgGR8BIzqMFUyYYaAdNHQFoCEdAmESqg/Tsp3V9lChoBkfAWqhenhsImmgHS7hoCEdAmEYwOFxn4HV9lChoBkfAUzFJBgNPQGgHS5loCEdAmEg9Rm9QGnV9lChoBkdAY+h1W8yvcWgHTVsBaAhHQJhJcuPFNtZ1fZQoaAZHQGqcA+hXbM5oB013AWgIR0CYSjwTufEodX2UKGgGR0BoC737DVH4aAdNUgFoCEdAmErw4bS7XnV9lChoBkfAUsJpudf9gmgHS65oCEdAmE7U3juKGnV9lChoBkfAUwSimEXcg2gHS6BoCEdAmE9xQemvXHV9lChoBkdAWWrWxyGSIWgHTegDaAhHQJhQzpkf9xZ1fZQoaAZHQGi9vHtF8XxoB02XAWgIR0CYVkVAAyVOdX2UKGgGR0BpS8dHUc4paAdNygFoCEdAmFa1LnLaEnV9lChoBkdAb/aXqqwQlWgHTSgBaAhHQJhWvwnYxtZ1fZQoaAZHQGcKYZuQ6p5oB01eAWgIR0CYV8PEbYK6dX2UKGgGR8BSkUK7ZnL8aAdLvmgIR0CYWBndfsu4dX2UKGgGR8A/Rm/WUbDNaAdNEgFoCEdAmFmM5fdAPnV9lChoBkfAU8xbpu/DcmgHTTsBaAhHQJhaNgBtDUp1fZQoaAZHwEGJ5kbxVhloB00BAWgIR0CYXjh4MWoFdX2UKGgGR0BTirjtG/etaAdN6ANoCEdAmF6HD3ueBnV9lChoBkfAUYrN4Z/CqWgHS7RoCEdAmF7ckhRqGnV9lChoBkdAbqYCnP3SKGgHTTgBaAhHQJhf0P/aQFN1fZQoaAZHwE/nXVbzK9xoB0vZaAhHQJhgvb0voNd1fZQoaAZHwE+6pLEk0JpoB006AWgIR0CYYVr9ETg3dX2UKGgGR8BZrKVhTfixaAdLz2gIR0CYZG4BV+7UdX2UKGgGR8BdAs7U5MlDaAdL0GgIR0CYZTj0cwQEdX2UKGgGR8BL0P4ubqhUaAdL9mgIR0CYZoYekpI+dX2UKGgGR8BQRqM72criaAdLw2gIR0CYZ5bLlmvodX2UKGgGR0BtPq1Cw8nvaAdN+AFoCEdAmGfBjz7MxHV9lChoBkfASyOEqUeMh2gHTSoBaAhHQJhqSr/82rJ1fZQoaAZHwE4AAbyYoiNoB00qAWgIR0CYbBj94u9OdX2UKGgGR8BKRXCj1wo9aAdLwGgIR0CYbil2eQMhdX2UKGgGR8BazOh0yP+5aAdL4GgIR0CYcQZccENfdX2UKGgGR0BssiprDZUUaAdNIQFoCEdAmHGjd+G47XV9lChoBkfAMt5mAbyYomgHS/5oCEdAmHIk0iyIHnV9lChoBkdAbl/k/bCaZ2gHTSEBaAhHQJh4NU0elsR1fZQoaAZHwEn5ShJyyUtoB0u9aAhHQJh4YoVmBe51fZQoaAZHP+Ldmg8KXv9oB00UAWgIR0CYeXwN9YwJdX2UKGgGR0BgN06q814xaAdN6ANoCEdAmHnW1YyO73V9lChoBkfAPlyXUpd8iWgHS95oCEdAmHqcNMGorHVlLg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 7813, "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:": "gAWV3AAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFm51bXB5Ll9jb3JlLm11bHRpYXJyYXmUjAZzY2FsYXKUk5SMBW51bXB5lIwFZHR5cGWUk5SMAmk4lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGJDCAQAAAAAAAAAlIaUUpSMBXN0YXJ0lGgIaA5DCAAAAAAAAAAAlIaUUpSMBl9zaGFwZZQpjAVkdHlwZZRoDowKX25wX3JhbmRvbZROdWIu", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 8, "n_steps": 16, "gamma": 0.999, "gae_lambda": 0.95, "ent_coef": 0.05, "vf_coef": 0.25, "max_grad_norm": 0.5, "normalize_advantage": false, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.123+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Mar 30 16:01:29 UTC 2025", "Python": "3.11.13", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.6.0+cu124", "GPU Enabled": "False", "Numpy": "2.0.2", "Cloudpickle": "3.1.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d99e65f620651f5950b61d6f967b1036815bbe53c0d355a0c0ce65d31d9ca68a
+size 165070

results.json

@@ -0,0 +1 @@
+{"mean_reward": 47.81046719999999, "std_reward": 135.89787599632015, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-07T14:42:05.191896"}