Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -196.56 +/- 94.46
+      value: -242.45 +/- 140.03
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.000125
+'learning_rate': 5e-05
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1735410519.2763f7ab14bb.3543.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dce301a8b835bce79f3e2b74c331cf0060517affc1bba156a8c77c7bb9f6391
+size 114300

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdad9ebbb8590f57f2d2449038a1c8383b836b0ccca75457c26a503b7e78191e
+oid sha256:9ecb40165f04dad50e7307957e9d5011d2f0ad678b639759735a1f4524005e1d
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -196.5622632606698, "std_reward": 94.45577608166926, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-28T18:28:02.128055"}
+{"env_id": "LunarLander-v2", "mean_reward": -242.45051973379117, "std_reward": 140.02578871013702, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-28T18:29:21.185505"}