Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -180.73 +/- 117.06
+      value: -116.46 +/- 38.78
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 2.5e-05
+'learning_rate': 0.0025
 'num_envs': 18
 'num_steps': 1024
 'anneal_lr': True

logs/events.out.tfevents.1720914529.5b2a566f3731.25023.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68ed1de5005ea3cbbd4ccedf15fe1de8e497913ca34b049c236dbed4e7b1a73b
+size 45857

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56fc5127d4ebf70aa5abeae233a34b91b001e26dc060ab34d83b990b25ecd4d2
+oid sha256:9b4c191940adfca796d649252af6702ccca1dc00a857b962e3df07f65ebee15a
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -180.72908652040817, "std_reward": 117.0600586827208, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-13T23:48:19.401589"}
+{"env_id": "LunarLander-v2", "mean_reward": -116.45662076828334, "std_reward": 38.78307779927838, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-13T23:49:04.424358"}