Push PPO agent to the Hub

README.md

@@ -0,0 +1,58 @@
+---
+tags:
+- LunarLander-v2
+- 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-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: -202.89 +/- 95.45
+      name: mean_reward
+      verified: false
+---
+
+# PPO Agent Playing LunarLander-v2
+
+This is a trained model of a PPO agent playing LunarLander-v2.
+
+# Hyperparameters
+{'exp_name': 'ppo'
+'seed': 1
+'torch_deterministic': True
+'cuda': True
+'track': False
+'wandb_project_name': 'cleanRL'
+'wandb_entity': None
+'capture_video': True
+'env_id': 'LunarLander-v2'
+'total_timesteps': 5000
+'learning_rate': 0.00025
+'num_envs': 8
+'num_steps': 2048
+'anneal_lr': True
+'gae': True
+'gamma': 0.99
+'gae_lambda': 0.95
+'num_minibatches': 32
+'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': 'AMZ2004/ppo-LunarLander-v2-AMZ'
+'batch_size': 16384
+'minibatch_size': 512}

logs/events.out.tfevents.1754231374.43abc99fdb1e.35050.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb26abb9b90b6db9be02a2e97b50069e45fe6170e2ed147c5baae66eda9e7120
+size 737

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:760c804c0e0cc3877a52c5c761c69dc3436e7c86b2a3c808057312454d7077e0
+size 147602

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -202.89347043112167, "std_reward": 95.45282050549824, "n_evaluation_episodes": 10, "eval_datetime": "2025-08-03T14:29:38.293371"}