Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -83.66 +/- 54.56
+      value: 89.60 +/- 50.03
       name: mean_reward
       verified: false
 ---
@@ -45,7 +45,7 @@ model-index:
 'gae': True
 'gamma': 0.999
 'gae_lambda': 0.98
-'num_minibatches': 4
+'num_minibatches': 64
 'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
@@ -56,6 +56,6 @@ model-index:
 'target_kl': None
 'repo_id': 'yaystevek/LunarLander-v2-scratch'
 'batch_size': 16384
-'minibatch_size': 4096}
+'minibatch_size': 256}
   ```
   

logs/events.out.tfevents.1693537826.3ba86102856c.20207.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f728e8b8f8c4d988bf2fa30e741f03d501503f453172c1f6afd94bdf9d3c333
+size 330185

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af043ec7cefa0fca327be8cf9b39a18a2347140ecda7863615dca639bc3b4d13
+oid sha256:94fe3b6139499431e3343850e12ef4c491092e6f542ba8d7f5ded71b2e21855c
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -83.66184538224437, "std_reward": 54.55955836127892, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-01T02:59:17.015253"}
+{"env_id": "LunarLander-v2", "mean_reward": 89.59568738624367, "std_reward": 50.0278710664372, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-01T03:30:06.274901"}