Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -176.44 +/- 115.63
+      value: -158.11 +/- 98.85
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.0001
+'learning_rate': 9e-05
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1714947642.71d3fa3d3a00.12436.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0da652893213f327b9518280a1b20d4f232d65d91f746c47e7381114c4acdf14
+size 111076

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:807d033f6139acb7000f3543f9f2ec6b1edd55f48f94709afd99acea45fd31e5
+oid sha256:3684831b3125526259e7b980918e98b3a744af49905f4af33eb97d2669c8044a
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -176.43558234545213, "std_reward": 115.62676171529867, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-05T22:19:49.651286"}
+{"env_id": "LunarLander-v2", "mean_reward": -158.10591385260986, "std_reward": 98.846102446971, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-05T22:21:26.714058"}