Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -204.14 +/- 103.11
+      value: -146.68 +/- 107.02
       name: mean_reward
       verified: false
 ---
@@ -40,7 +40,7 @@ model-index:
 'total_timesteps': 50000
 'learning_rate': 1e-05
 'num_envs': 6
-'num_steps': 88
+'num_steps': 98
 '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': 528
-'minibatch_size': 132}
+'batch_size': 588
+'minibatch_size': 147}
   ```
   

logs/events.out.tfevents.1746579351.b45e59692ef7.20090.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb8a0dab251cd08401a0da2c875cc899e9200378b5157191779457941c8d6b82
+size 105934

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfa0074f0bf22f5816736c9213a8c3439aa276a409a70fa4d58e56373d75376d
+oid sha256:40aeb8c1755a53aec3b776e8c628e6a273645c483285c7f4b9e476a3f08d3622
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -204.1428024975208, "std_reward": 103.11422429726542, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-07T00:54:12.849330"}
+{"env_id": "LunarLander-v2", "mean_reward": -146.67560210914849, "std_reward": 107.02481737452253, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-07T00:56:28.646860"}