Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -127.73 +/- 82.94
+      value: -57.43 +/- 61.21
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1676581627.xps.3059.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b5be086af63154142bcb471427a4db4d0dcfc1ff69bbd835bfac6b3f70c4051
+size 1260198

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:825c8e948df4a6017f1b2991d7d0a8ed73f871d363b6819bc0d0d2a6d98217fb
+oid sha256:8d34921609152b9cbbf618c78a4ccfc302e6876e9a19e5f44689cd1f8ed2136d
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -127.72989887556496, "std_reward": 82.94377338933832, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-16T21:06:15.187575"}
+{"env_id": "LunarLander-v2", "mean_reward": -57.42590501970475, "std_reward": 61.214521856727714, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-16T21:30:53.284297"}