Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -191.30 +/- 117.76
+      value: -143.67 +/- 104.33
       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': 100000
 'learning_rate': 5e-05
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1714949926.71d3fa3d3a00.22354.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a6d34cbd84bd6208a4adc1011a19345d8a04a651e7f846614f34751be23f5d1
+size 227754

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0792a2b515886e3c981b32975c6cd623782aaf2e473ea4c69586eefe0ff8736b
+oid sha256:fc4440e4d2e67eb34e3fef5529889e2aee114264c46167d6bb5ee4e2198c7521
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -191.2986382309057, "std_reward": 117.76285338974455, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-05T22:57:13.155322"}
+{"env_id": "LunarLander-v2", "mean_reward": -143.66767441508628, "std_reward": 104.33212867200926, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-05T23:00:06.128740"}