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: 43.72 +/- 83.56
+      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': 0.00025
+'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': 'FranticUser/LunarLander-v2'
+'batch_size': 512
+'minibatch_size': 128}
+  ```
+  

logs/events.out.tfevents.1770183206.146a01270f08.23817.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6a23901f2c210286d6c6d2946be60c2f748b69777c3504f32e3e5598647130f
+size 503092

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16bf5b8b731ae5f5dc73aacccef26b3c31996145f64d6b8b2262231074282e7c
+size 43419

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6855436bfb64aaebf09d1b4d42fb34e705a0c994fcc1295a676acb51642da8a
+size 167600

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v3", "mean_reward": 43.72374409867977, "std_reward": 83.55838393799614, "n_evaluation_episodes": 10, "eval_datetime": "2026-02-04T05:39:16.827609"}