Push agent to the Hub

.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 +1,61 @@
+---
+tags:
+- Pixelcopter-PLE-v0
+- ppo
+- deep-reinforcement-learning
+- reinforcement-learning
+- custom-implementation
+- deep-rl-course
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Pixelcopter-PLE-v0
+      type: Pixelcopter-PLE-v0
+    metrics:
+    - type: mean_reward
+      value: 184.10 +/- 135.63
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing Pixelcopter-PLE-v0
+
+  This is a trained model of a PPO agent playing Pixelcopter-PLE-v0.
+    
+  # Hyperparameters
+  ```python
+  {'exp_name': 'ppo_pixelcopter'
+'seed': 1
+'torch_deterministic': True
+'cuda': True
+'track': False
+'wandb_project_name': 'cleanRL'
+'wandb_entity': None
+'capture_video': False
+'env_id': 'Pixelcopter-PLE-v0'
+'total_timesteps': 10000000
+'learning_rate': 0.00025
+'num_envs': 8
+'num_steps': 1024
+'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
+'repo_id': 'nasnoussi/ppo-Pixelcopter-v1'
+'batch_size': 8192
+'minibatch_size': 2048}
+  ```
+  

logs/events.out.tfevents.1740864659.MacBook-Pro-de-anis-2.local.66030.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b13de1849631993cfb073d0e9019720eaac9c11a9769f68f62788ed4f55f5b53
+size 3876512

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aba47ec023d7a2bf56fd26a1680e71f8730fb7192044a5ba0ceaef7bc5704e1
+size 145554

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83309350c76f230c61988a5c44014caef57266a9803c5452315700c4ac279220
+size 143885

results.json

@@ -0,0 +1 @@
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 184.1, "std_reward": 135.62997456314736, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-01T22:43:28.445434"}