Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -99.99 +/- 51.57
+      value: -133.01 +/- 59.83
       name: mean_reward
       verified: false
 ---
@@ -52,8 +52,8 @@ model-index:
 'clip_coef': 0.2
 'clip_vloss': True
 'ent_coef': 0.015
-'vf_coef': 0.75
-'max_grad_norm': 0.75
+'vf_coef': 0.25
+'max_grad_norm': 0.25
 'target_kl': None
 'repo_id': 'mgmeskill/ppo-LunarLander-v3'
 'batch_size': 512

logs/events.out.tfevents.1691894203.4c5d58e91a6c.225.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82c9a129703f07aef00827ce5f99a1cf0f3fec27cbfe7d58eec7e06c21980fea
+size 216469

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f13198e1466ec011aeede1eca79b4f85e6f120b033e44a7b46a1a23c13bbf27
+oid sha256:760136cdba079d759c4e24069c2b470074bb9f8d9a00a677ecd8ad53bd9af41e
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -99.99204338679954, "std_reward": 51.568848623875674, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:36:19.263890"}
+{"env_id": "LunarLander-v2", "mean_reward": -133.01069418612266, "std_reward": 59.82798516461417, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:38:06.442848"}