Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -121.68 +/- 87.76
+      value: -4.14 +/- 61.83
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 600000
+'total_timesteps': 700000
 'learning_rate': 5e-05
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1714953981.71d3fa3d3a00.39395.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f48f65585308666627de784bec125f81d8f17cd53697f6857ccf5939d36cf438
+size 1172210

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca05ce7be0fb048fcbd6e04d147a0db4b695c0f49b9ab69ad056530d4e1a1bd1
+oid sha256:1c63e7a8552c42ce1c723655e6d971692aa87eb8b8847a7d4105878055aef03c
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -121.67820025913845, "std_reward": 87.75831564844681, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-06T00:04:20.538201"}
+{"env_id": "LunarLander-v2", "mean_reward": -4.1426220469325346, "std_reward": 61.825991932123856, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-06T00:18:25.790056"}