Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -170.70 +/- 111.53
+      value: -176.19 +/- 123.62
       name: mean_reward
       verified: false
 ---
@@ -45,7 +45,7 @@ model-index:
 'gae': True
 'gamma': 0.999
 'gae_lambda': 0.98
-'num_minibatches': 256
+'num_minibatches': 8
 'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
@@ -56,6 +56,6 @@ model-index:
 'target_kl': None
 'repo_id': 'anders0204/ppo-LunarLander-v2'
 'batch_size': 16384
-'minibatch_size': 64}
+'minibatch_size': 2048}
   ```
   

logs/events.out.tfevents.1696843686.Anderss-MacBook-Pro-4.local.50731.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e107a9514b1b95234cbe6f3abf35b2cd2c2256ef8a33a9ef1d4d1c6d68ea06f0
+size 737

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -170.69846007731394, "std_reward": 111.52902773549665, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-09T11:26:26.235947"}
+{"env_id": "LunarLander-v2", "mean_reward": -176.1946040436812, "std_reward": 123.61633373612632, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-09T11:28:12.628880"}