Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -69.13 +/- 64.51
+      value: -59.53 +/- 74.79
       name: mean_reward
       verified: false
 ---
@@ -51,7 +51,7 @@ model-index:
 'clip_coef': 0.2
 'clip_vloss': True
 'ent_coef': 0.01
-'vf_coef': 0.25
+'vf_coef': 0.5
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'naeisher/LunarLander-v2'

logs/events.out.tfevents.1679877542.2a0c170730d9.67844.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88b57733f4fcb2821603c69a5f70cd7036e254c7f270d6d24f289271161e4abd
+size 100430

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dba0123b0c3e8c8044da3b3c0a9a49a6d84d3b2afa1424c23d65542b35b4e80a
+oid sha256:5c8b68f4adfe3439b02e07a5ccd712524a84bca3da251794593abc64b6814057
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -69.12990195762707, "std_reward": 64.50515616992922, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-27T00:36:56.229472"}
+{"env_id": "LunarLander-v2", "mean_reward": -59.52789658298492, "std_reward": 74.79089803812734, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-27T00:40:52.538807"}