Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -126.62 +/- 67.05
+      value: 30.27 +/- 83.73
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1683839641.decd130615ec.3239.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8afe64cce736351f432a6f7323c177c6e40efacb80c81c0af54f8ee38f719a7e
+size 669774

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e304481d929ee4afe57bfc2f353b7139b5b63a076ea2edd03f0735d5bc715ad
+oid sha256:d4f48c7c21e403a40dbe66a6f0ec64e4be618b551ce4706017b38b523d1469a6
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -126.6219797024492, "std_reward": 67.04719672277007, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-11T21:12:35.837808"}
+{"env_id": "LunarLander-v2", "mean_reward": 30.273896890394553, "std_reward": 83.72754625210915, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-11T21:30:53.068050"}