Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -179.11 +/- 121.96
+      value: -196.56 +/- 94.46
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.00025
+'learning_rate': 0.000125
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1735410435.2763f7ab14bb.3134.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2086d06924c88bccbce2b099e09e78641f8b6221e45723500d371a68e571e2f5
+size 110703

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
+oid sha256:fdad9ebbb8590f57f2d2449038a1c8383b836b0ccca75457c26a503b7e78191e
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -179.11266606615823, "std_reward": 121.96496332309901, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-27T21:25:47.957616"}
+{"env_id": "LunarLander-v2", "mean_reward": -196.5622632606698, "std_reward": 94.45577608166926, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-28T18:28:02.128055"}