Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -192.49 +/- 112.30
+      value: -146.89 +/- 80.73
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 0.0003
+'learning_rate': 0.005
 'num_envs': 10
 'num_steps': 2048
 'anneal_lr': True

logs/events.out.tfevents.1679138449.0bfcb7fd5bd3.6644.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e83cd8cfda20f4de941aede279ec31bce490102f8d78fc4037c9065539795aa0
+size 100503

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2767e56f26358e76f08e8e26f4d3bb99d4313361ec70ebe6b25a4ddd30523082
+oid sha256:b97d566e3f5c46187ee255c1502885095cf174aaff87503e1e77e09d92126c44
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -192.49175212311007, "std_reward": 112.30339322913036, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-18T11:20:01.457100"}
+{"env_id": "LunarLander-v2", "mean_reward": -146.88957016180473, "std_reward": 80.73300118628052, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-18T11:21:24.120881"}