Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -194.05 +/- 98.77
+      value: -188.61 +/- 136.53
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': 'andersva'
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 10000
+'total_timesteps': 100000
 'learning_rate': 0.0001
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1696597030.Anderss-MacBook-Pro-4.local.43511.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54f4fd1a5d087a91378ba800544d7cc5de0909272fdc668530e7e869d640e67b
+size 240889

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:013b0ddedd571b11821a61970136f108c25ea1f4d6dfdab42164ce0722efddcb
+oid sha256:b74b502baec933c2309f5eed6d1a36b750d561be13d7035946a6b7662c7c4bbd
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -194.05163856474317, "std_reward": 98.76859725498151, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-06T14:56:00.438104"}
+{"env_id": "LunarLander-v2", "mean_reward": -188.60958267217347, "std_reward": 136.5259754197802, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-06T15:01:14.594338"}