Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -132.75 +/- 45.39
+      value: -171.15 +/- 91.35
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 0.0001
+'learning_rate': 0.00023
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1708629077.27eacc152b6c.15317.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c2cf0d0baf2f9a68de40a41caab203c67beeffa8291df014d94cbeda5f3aa30
+size 218585

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bab92906bdc8a65a6943246324cca4dad34aaf61f5a775a347463b5555f99f0
+oid sha256:610d879ecd2d5787507804ce5d052cef9506b762e7dfd1c145f9371ff58cc1b2
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -132.75412597112125, "std_reward": 45.39155430237143, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-22T19:08:55.136470"}
+{"env_id": "LunarLander-v2", "mean_reward": -171.14939209866324, "std_reward": 91.34699282054007, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-22T19:12:42.508391"}