Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -27.28 +/- 17.06
+      value: -62.33 +/- 80.88
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 400000
+'total_timesteps': 200000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1683541507.96178242aa96.16850.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e6348946c7e8b8d3b3236d513a793122934adae49d1885cf441da580eef3eeb
+size 383745

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e65bb607088a6582112b461b23d4481ccf840dfc9a1ad7f9b1d1e38c841a622
+oid sha256:e96cb13a843a3f442df10aa22e370701470b91bd226803688fe15c05e7af6c6d
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -27.279308704070775, "std_reward": 17.058221780624844, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-08T10:19:16.345327"}
+{"env_id": "LunarLander-v2", "mean_reward": -62.32716087469778, "std_reward": 80.87596184919101, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-08T10:28:20.720974"}