Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -182.10 +/- 108.20
+      value: -32.39 +/- 77.46
       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': 200000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1701103755.d0ce2476db28.7531.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6f91633adb98db8c969bae32eb13ca3810a1bd702ede0fd3fb0160270058b1e
+size 356206

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
+oid sha256:1efdb17a91d165475a33b5df37ed9e8049c65b910cf084fd420eda94a1e63838
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -182.09961306434374, "std_reward": 108.20390781537346, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-27T16:47:59.321389"}
+{"env_id": "LunarLander-v2", "mean_reward": -32.38524538206579, "std_reward": 77.45762868114686, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-27T16:52:45.142566"}