Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -135.40 +/- 117.23
+      value: -182.38 +/- 62.36
       name: mean_reward
       verified: false
 ---
@@ -40,7 +40,7 @@ model-index:
 'total_timesteps': 50000
 'learning_rate': 1e-05
 'num_envs': 6
-'num_steps': 365
+'num_steps': 165
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'Ari8/ppo-LunarLander-v2_unit8'
-'batch_size': 2190
-'minibatch_size': 547}
+'batch_size': 990
+'minibatch_size': 247}
   ```
   

logs/events.out.tfevents.1746578498.b45e59692ef7.16347.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14bc8b3bd499aa3c0eb0425ee70f11525e0edce23a685c27488e7f7fcc17003f
+size 87145

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ce0b02aafd6a0569cd42539fb755bd4e0659ed596cc06ef557e5c37010c7d2c
+oid sha256:805cc3f8d7a9e068e4c173e54262a7510367033f8e2e31a4cab03066c9379f77
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -135.39870510537992, "std_reward": 117.23197675409425, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-07T00:40:40.064007"}
+{"env_id": "LunarLander-v2", "mean_reward": -182.37665860979823, "std_reward": 62.3579062790844, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-07T00:42:12.031663"}