Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -175.83 +/- 75.11
+      value: -221.38 +/- 108.44
       name: mean_reward
       verified: false
 ---
@@ -48,7 +48,7 @@ model-index:
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
-'clip_coef': 0.1
+'clip_coef': 0.3
 'clip_vloss': True
 'ent_coef': 0.01
 'vf_coef': 0.5

logs/events.out.tfevents.1682327475.85ccc7867d7f.11021.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c49dce74906b035f461c3e218a266dcfe3521e41ac94875bd3d427673b450548
+size 109724

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1448eea0f2cc95f3595de0c642f441759058282e5c13bfa86cf1aadd5c8561a8
+oid sha256:ed0844daf609a95160287a7fb90fb8c35bdf316b8860206870511b3db7ac5bbe
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -175.82676804532449, "std_reward": 75.10502414939737, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-24T09:10:30.591945"}
+{"env_id": "LunarLander-v2", "mean_reward": -221.3831474591957, "std_reward": 108.4417492689173, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-24T09:12:05.406706"}