Push Reinforce agent to the Hub

.gitattributes

@@ -29,3 +29,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,29 @@
+---
+tags:
+- CartPole-v1
+- ppo
+- reinforcement-learning
+- custom-implementation
+- deep-rl-class
+model-index:
+- name: CleanRLTest
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 239.10 +/- 117.52
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+---
+
+  # **PPO** Agent playing 
+  This is a trained model of a ***PPO** agent playing CartPole-v1.
+  To learn to use this model and train yours check Unit 8 of the Deep Reinforcement Learning Class: https://github.com/huggingface/deep-rl-class/tree/main/unit5
+  {'exp_name': 'ppo', 'seed': 1, 'torch_deterministic': True, 'cuda': True, 'track': False, 'wandb_project_name': 'cleanRL', 'wandb_entity': None, 'capture_video': False, 'env_id': 'CartPole-v1', 'total_timesteps': 50000, 'learning_rate': 0.00025, 'num_envs': 4, 'num_steps': 128, 'anneal_lr': True, 'gae': True, 'gamma': 0.99, 'gae_lambda': 0.95, 'num_minibatches': 4, 'update_epochs': 4, 'norm_adv': True, 'clip_coef': 0.2, 'clip_vloss': True, 'ent_coef': 0.01, 'vf_coef': 0.5, 'max_grad_norm': 0.5, 'target_kl': None, 'batch_size': 512, 'minibatch_size': 128}
+
+  Boom
+  

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4873c6f52f0fd40fb673a2357545e20aa02bb2dea7ee0f81199d920460cc1d88
+size 40129

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c75a34d6c3269990b3dbb52a4ed9730ef3579e1db0b0f29d93c7ae726aca2a9b
+size 18101

results.json

@@ -0,0 +1 @@
+{"env_id": "CartPole-v1", "mean_reward": 239.1, "n_evaluation_episodes": 10, "eval_datetime": "2022-08-02T17:45:10.432182"}