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

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -107.75 +/- 0.00
+      value: -182.89 +/- 0.00
       name: mean_reward
       verified: false
 ---
@@ -30,17 +30,17 @@ model-index:
     ```python
     {'exp_name': 'ppo'
 'gym_id': 'LunarLander-v2'
-'learning_rate': 0.00025
+'learning_rate': 0.0003
 'seed': 1
-'total_timesteps': 50000
+'total_timesteps': 1000000
 'torch_deterministic': True
 'cuda': True
 'track': False
 'wandb_project_name': 'cleanRL'
 'wandb_entity': None
 'capture_video': False
-'num_envs': 4
-'num_steps': 128
+'num_envs': 8
+'num_steps': 256
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,8 +55,8 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'LucasBlock/ppo-pytorch-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128
+'batch_size': 2048
+'minibatch_size': 512
 'env_id': 'LunarLander-v2'}
     ```
     

logs/events.out.tfevents.1761950871.RL-43414990.71824.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59bdd34ab6b4d274ba9d8364e2b8f4a179a6430b62db95ccdad98ba07a720cf8
+size 541364

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af60a66c2bca61005ddf24cd44177734d105d7581691d9f9417b211e3c866da7
+oid sha256:7e0e2509b072d3810342faf9c2035395441ee25b6f3e4f627f2348b489f737e3
 size 43291

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -107.75017892998588, "std_reward": 0.0, "n_evaluation_episodes": 10, "eval_datetime": "2025-10-31T22:41:35.000481"}
+{"env_id": "LunarLander-v2", "mean_reward": -182.8945033578778, "std_reward": 0.0, "n_evaluation_episodes": 10, "eval_datetime": "2025-10-31T23:06:47.933194"}