Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -159.46 +/- 97.40
+      value: 16.83 +/- 111.18
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 10000
+'total_timesteps': 100000
 'learning_rate': 0.001
 'num_envs': 4
 'num_steps': 1024

logs/events.out.tfevents.1691959634.bcadd1928d08.12220.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:042eb06fe01b0143a909e738aaef13d0d32cae130c5093657512d8bdc3170d44
+size 70141

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01cb2c7deeba9912724733e05c9e07552cbf46a08cc97798d378b8339ee09448
+oid sha256:396ec0c6c24c34c3aed94f27f5556a495e77f8c5972c3859c414f450e62e67ff
 size 4285797

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -159.46132372221183, "std_reward": 97.3977647762934, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T20:45:57.957686"}
+{"env_id": "LunarLander-v2", "mean_reward": 16.833918908828444, "std_reward": 111.18400947427422, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T20:50:07.554044"}