Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 225.90 +/- 71.33
+      value: 386.70 +/- 96.63
       name: mean_reward
       verified: false
 ---
@@ -44,12 +44,12 @@ model-index:
 'num_steps': 384
 'anneal_lr': True
 'gae': True
-'gamma': 0.985
-'gae_lambda': 0.94
+'gamma': 0.995
+'gae_lambda': 0.95
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.225
+'clip_coef': 0.195
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5

logs/events.out.tfevents.1708907895.0d8f6edb1bcc.955.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00c644261cdbde3eee0d344ca5c39d73697a512fa3f64e723555528356ab9954
+size 710868

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63d872a0867ed5d76310af353204cbe65f94feb5853ee9c365369088bb232521
+oid sha256:eafd0a4ba75cf6c491cf949b1d98372ced12b71954bddcd6bce5de6bfafa76ac
 size 40466

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 225.9, "std_reward": 71.32804497531109, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-26T00:36:57.478614"}
+{"env_id": "CartPole-v1", "mean_reward": 386.7, "std_reward": 96.63441415975988, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-26T00:43:32.650605"}