Push agent to the Hub

README.md

@@ -0,0 +1,59 @@
+---
+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: 166.93 +/- 95.27
+      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': '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': 0.0003
+'num_envs': 8
+'num_steps': 256
+'anneal_lr': True
+'gae': True
+'gamma': 0.99
+'gae_lambda': 0.95
+'num_minibatches': 8
+'update_epochs': 10
+'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': 'Petheron/ppo-LunarLander-v2-unit8'
+'batch_size': 2048
+'minibatch_size': 256}
+```
+  

logs/events.out.tfevents.1779079843.5afa1a1050cd.25426.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31abe57b5bd269834565f72a90dd1f2e555ab232442ba20b3bdde827d3f9a98d
+size 126336

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25c70fb50d04952771f12fa7aa6ca870919d16ccc555707078d10fd9c5475fcb
+size 43419

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v3", "mean_reward": 166.92812681656034, "std_reward": 95.26864453245717, "n_evaluation_episodes": 10, "eval_datetime": "2026-05-18T04:55:10.191646"}