Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -100.21 +/- 67.79
+      value: -206.42 +/- 95.17
       name: mean_reward
       verified: false
 ---
@@ -47,7 +47,7 @@ model-index:
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 4
-'update_epochs': 4
+'update_epochs': 1
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True

logs/events.out.tfevents.1691895298.4c5d58e91a6c.225.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b41bc536d36907b08388e099cea6ea1cb2a9f0e05d016effc47c55ddd986dae1
+size 215603

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d8698b202d5caf285d4f840fd837056492884e0e71ffb1e6267c622c2e81452
+oid sha256:9996801abd03add207198d5262985244cea04cc33a26289b3ca513c06f909138
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -100.2069420919785, "std_reward": 67.7877861350826, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:54:36.813636"}
+{"env_id": "LunarLander-v2", "mean_reward": -206.42487658721757, "std_reward": 95.16599009967193, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T02:56:21.720477"}