Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -106.08 +/- 77.00
+      value: -216.18 +/- 115.42
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 10000
-'learning_rate': 0.001
+'learning_rate': 0.0001
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1677780462.6c4e5c51f044.16151.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c4f0632e720ca08d0e768b5fb3262fd7673a9d8e5602b3687f7c5d29847074d
+size 22013

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de5a6e339b4256c1f6f6b16baf2a1baa772084cddb7fadb98928957229b29b58
+oid sha256:57e56b1b19d087c6db71a56d0ddc61ec9f2715d5bbbc2fe8851c8eca39dc1a90
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -106.07702309290815, "std_reward": 77.00171347872302, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-02T18:07:05.359811"}
+{"env_id": "LunarLander-v2", "mean_reward": -216.17740745274355, "std_reward": 115.41958273359432, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-02T18:07:57.690611"}