Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -92.45 +/- 79.72
+      value: -139.95 +/- 40.61
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.01
+'learning_rate': 0.1
 'num_envs': 4
 'num_steps': 300
 'anneal_lr': True

logs/events.out.tfevents.1677778921.6c4e5c51f044.9210.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3acc6df84e9881cd0cdb0edf0934d60db0721c5b338ede19d4b7a3715d243c33
+size 107896

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8081c85a814ceaa0645287c738122fdd0b47ad40edd66adf5777c71b32550bee
+oid sha256:8400ea34a98a85e180abd047a7fe0caf8a247ee329059e8755717cdb3751fd34
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -92.44806132550572, "std_reward": 79.7219557687308, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-02T17:41:01.839171"}
+{"env_id": "LunarLander-v2", "mean_reward": -139.95133749417, "std_reward": 40.61485880209634, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-02T17:42:32.960148"}