Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 70.49 +/- 43.95
+      value: 85.23 +/- 68.57
       name: mean_reward
       verified: false
 ---
@@ -45,8 +45,8 @@ model-index:
 'gae': True
 'gamma': 0.999
 'gae_lambda': 0.98
-'num_minibatches': 4
-'update_epochs': 10
+'num_minibatches': 32
+'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
@@ -56,6 +56,6 @@ model-index:
 'target_kl': None
 'repo_id': 'andyleow/PPO-LunarLander-v2'
 'batch_size': 16384
-'minibatch_size': 4096}
+'minibatch_size': 512}
   ```
   

logs/events.out.tfevents.1684364579.a82ae466d056.8699.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f505a725baac55b1802ebfef04f7ab655474a0eac280611e8b6526bde56a6a08
+size 353741

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e17523fbeebb0d4fdb79282b61a2d03d0c70b941435f2231749b653484398790
+oid sha256:9c3c01b29fbcf9d19b9c60ead84f6c14a4e62e6f4ef1f9a6d10007e99aed577c
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 70.49066525430779, "std_reward": 43.95125837867714, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-17T22:57:30.390658"}
+{"env_id": "LunarLander-v2", "mean_reward": 85.2315770074154, "std_reward": 68.57322870026267, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-17T23:20:25.457980"}