Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -76.57 +/- 68.38
+      value: -93.55 +/- 109.16
       name: mean_reward
       verified: false
 ---
@@ -43,14 +43,14 @@ model-index:
 'num_steps': 2048
 'anneal_lr': True
 'gae': True
-'gamma': 0.95
+'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 32
 'update_epochs': 10
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True
-'ent_coef': 0.01
+'ent_coef': 0.02
 'vf_coef': 0.2
 'max_grad_norm': 0.5
 'target_kl': None

logs/events.out.tfevents.1679877991.2a0c170730d9.69780.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:217ab756b7c38fd77c2225ce1fb06a8308ecb9be5441db016eb7b06352f340ea
+size 104276

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7050cea40f2d88272a680248b967610b0a668e1270c90d14bb67eb3f364cdcea
+oid sha256:742e33239069cbafcae4f15f5fa44cbe02955071563e6b2b23e99a7eb8e868ea
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -76.56597286686862, "std_reward": 68.38210889427033, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-27T00:45:45.883448"}
+{"env_id": "LunarLander-v2", "mean_reward": -93.55314124489209, "std_reward": 109.1596723165435, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-27T00:48:18.298014"}