Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -104.18 +/- 83.56
+      value: -128.36 +/- 98.71
       name: mean_reward
       verified: false
 ---
@@ -31,7 +31,7 @@ model-index:
   {'exp_name': 'ppo'
 'seed': 1
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 50000
 'target_kl': None
 'max_grad_norm': 0.5
 'vf_coef': 0.5
@@ -43,7 +43,7 @@ model-index:
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
-'num_minibatches': 4
+'num_minibatches': 8
 'update_epochs': 4}
   ```
   

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4f0bc0f1503a07837560199df54821ffc0e0a4e66cafdfeaa50612bad3296e9
+oid sha256:fc20c2342b8d4a911521b6df6e8880386530f1800afd273c5150eae72c79fbc0
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -104.1814593575411, "std_reward": 83.55580372276808, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-27T16:19:24.156573"}
+{"env_id": "LunarLander-v2", "mean_reward": -128.3617931476985, "std_reward": 98.71232303309957, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-27T16:22:32.693102"}