Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -203.97 +/- 125.02
+      value: -106.74 +/- 43.14
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': True
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.00025
+'learning_rate': 0.007
 'num_envs': 16
 'num_steps': 1024
 'anneal_lr': True

logs/events.out.tfevents.1693536405.3ba86102856c.13826.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e66b42fea986b5a3564fea91dd7c70a95a47f233379e180c8399cf1ad5391484
+size 60744

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c6c00696a0d337477f5e5417456f5de0e6c98d87eaf28e7afae24609d705d0d
+oid sha256:96b74a2201feb6dcf10536ed6baf7008fce337352428a44d8ff9da678ec29cae
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -203.96795814352873, "std_reward": 125.02049746905875, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-01T02:45:58.542834"}
+{"env_id": "LunarLander-v2", "mean_reward": -106.74236945668233, "std_reward": 43.141242979724055, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-01T02:47:11.429020"}