Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -29.23 +/- 20.99
+      value: 64.78 +/- 133.53
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 1000000
-'learning_rate': 0.00025
+'learning_rate': 0.003
 'num_envs': 16
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1677021882.aa7f54cef753.47078.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ed53bd42d86fc160727ca0c83d0018f8f47f1564160dc7a75aade2ee568a458
+size 583378

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:084895f32631410ce3795e6e48cff476bf14b9bfb601be206aabfe699d4d0cf2
+oid sha256:a4bb8c574855a5a6d97affd172f8cbe091678080ebd7ec5875de3160fe189963
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -29.232958359026014, "std_reward": 20.99323555016296, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-21T23:04:29.230659"}
+{"env_id": "LunarLander-v2", "mean_reward": 64.77789162087473, "std_reward": 133.52746329873193, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-21T23:39:32.402623"}