Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -155.11 +/- 72.85
+      value: -241.01 +/- 140.47
       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': 1e-05
 'num_envs': 4
 'num_steps': 512
 'anneal_lr': True

logs/events.out.tfevents.1718025538.887b5cfc0142.12883.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:908f53178fc089a77d1855d88f55c0ddb7e092241ac32520b7eaf7c92dbef166
+size 76188

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6c5823477f6a37bd9194edb9f45af0d3606ab6a06ee10c233282eadf2a1d850
+oid sha256:4f07b1b08be38f4670bcf36173b8ffae2cccd31c81bb92664307eaa120d0f012
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -155.10927752489494, "std_reward": 72.85296879332041, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T13:17:47.166457"}
+{"env_id": "LunarLander-v2", "mean_reward": -241.0094816404568, "std_reward": 140.47431516175723, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T13:19:50.546744"}