Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -4.14 +/- 61.83
+      value: 1.78 +/- 62.26
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 700000
+'total_timesteps': 800000
 'learning_rate': 5e-05
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1714955973.71d3fa3d3a00.47707.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8e1204235bc65c2270bb43642ec535965965b89f46449213752aa5f7c2c814b
+size 1238287

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c63e7a8552c42ce1c723655e6d971692aa87eb8b8847a7d4105878055aef03c
+oid sha256:e2f3e185724e0a971bcf8f1155b7348090f2021d11696227e79ca16df233ce3c
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -4.1426220469325346, "std_reward": 61.825991932123856, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-06T00:18:25.790056"}
+{"env_id": "LunarLander-v2", "mean_reward": 1.7838630532821327, "std_reward": 62.25949755636738, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-06T00:55:00.024315"}