Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -144.86 +/- 69.98
+      value: -180.55 +/- 108.68
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1714949664.71d3fa3d3a00.21168.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17d90efefadf1ce59f8d93d3562187e79cd0f6494a847d406ed7a029e3773802
+size 110093

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf4a7fde3320b1226867f811244d8c33574eca701ec88ceee90bda5c8724f5d8
+oid sha256:ea7adaf29ec4a7754b07ad326b8010d322ac5eb5ac24d758e971d51f95c5895e
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -144.86024537047396, "std_reward": 69.9824089669883, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-05T22:53:17.855296"}
+{"env_id": "LunarLander-v2", "mean_reward": -180.55414330065565, "std_reward": 108.68069002480259, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-05T22:55:06.908732"}