Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 2.53 +/- 66.59
+      value: -94.87 +/- 85.63
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 0.0005
+'learning_rate': 0.0001
 'num_envs': 4
 'num_steps': 1024
 'anneal_lr': True

logs/events.out.tfevents.1691959338.bcadd1928d08.10832.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:014008268d53cc8f32a11720d13357bd12cafe8e86af5050f80b171bda2ecf68
+size 106096

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f12ac369774e0cfc3ddc6b9a158b5e7e4b68f0d4d7134018f26e0cae0b537ee
-size 42597
+oid sha256:7060a96771d52696a93e474005107866a7cd2c6bb3d3fcce9cc7769ef908d41f
+size 4285797

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 2.5314041975983317, "std_reward": 66.59180341747874, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T20:27:01.195740"}
+{"env_id": "LunarLander-v2", "mean_reward": -94.86771239036132, "std_reward": 85.62780819319504, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T20:44:20.187452"}