Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 113.19 +/- 85.50
+      value: 125.56 +/- 113.05
       name: mean_reward
       verified: false
 ---
@@ -38,9 +38,9 @@ model-index:
 'capture_video': True
 'env_id': 'LunarLander-v2'
 'total_timesteps': 250000
-'learning_rate': 0.01
+'learning_rate': 0.005
 'num_envs': 4
-'num_steps': 128
+'num_steps': 512
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'wilt8/ppo-CleanRL-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 2048
+'minibatch_size': 512}
   ```
   

logs/events.out.tfevents.1725426762.coder-william-william-gpu-dev-01-5fd55f9c84-plnfx.1589799.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c4758a586beee221ac139b3083690b3899ea062e1a1308bd2e6a2ad429337a5
+size 145536

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:998e8ab73235f11e375d238a44e3a29eedd328a03ea817cb38e2edd536eb6c68
+oid sha256:972b5aeed163f692822206eb35e1cd53e126cb285d05ad0395ef5d92941fd84f
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 113.19222366945628, "std_reward": 85.49854242531748, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-04T13:11:31.249425"}
+{"env_id": "LunarLander-v2", "mean_reward": 125.5613769820333, "std_reward": 113.05206421587572, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-04T13:16:06.945384"}