Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -145.85 +/- 62.50
+      value: 116.42 +/- 30.24
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 2000
+'total_timesteps': 500000
 'learning_rate': 0.0001
 'num_envs': 4
 'num_steps': 1024

logs/events.out.tfevents.1695083433.f7ab440643c4.32218.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3270d8cee70ba4a9b4c428c8f9d924c60092dba4cad78eaa6a8842eb2cb29e5
+size 207051

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d415ace67605d0e4d171521ebcb0c7fcb2053e5d8fef4373af078321b4f6b4a
+oid sha256:295f3581a754fcbfc8a324292d6d6b1526a312b5fa81c858c96d65ec491ae288
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -145.84706003111293, "std_reward": 62.50342771570537, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-19T00:30:17.292877"}
+{"env_id": "LunarLander-v2", "mean_reward": 116.42329982236083, "std_reward": 30.243902399850842, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-19T00:49:04.867586"}