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:
+- LunarLander-v3
+- 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: LunarLander-v3
+      type: LunarLander-v3
+    metrics:
+    - type: mean_reward
+      value: 1.49 +/- 0.92
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing LunarLander-v3
+
+  This is a trained model of a PPO agent playing LunarLander-v3.
+    
+  # Hyperparameters
+  ```python
+  {'exp_name': 'hugging_face_ppo'
+'seed': 1
+'torch_deterministic': True
+'cuda': True
+'track': False
+'wandb_project_name': 'cleanRL'
+'wandb_entity': None
+'capture_video': False
+'env_id': 'LunarLander-v3'
+'total_timesteps': 500000
+'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
+'repo_id': 'Emptier8126/ppo-LunarLander-v3'
+'batch_size': 512
+'minibatch_size': 128}
+  ```
+  

logs/events.out.tfevents.1767115194.SLIMBOOK.30208.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30c269264c7dc9f80a4035a3713ae307135f6a352541d7779a1183f20db00946
+size 588289

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386f7e7ed09e2ec1fcf9e6f1fc4ec5c4ea4e9448c08e344f04884487cb26f72b
+size 43419

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2613c13f1436f9b7bca518c620a93fe8b3ce99defd2a0c7c80267d58ced6a16e
+size 245719

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v3", "mean_reward": 1.4863034749715356, "std_reward": 0.9175640238075906, "n_evaluation_episodes": 10, "eval_datetime": "2025-12-30T14:24:22.839832"}