Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -128.30 +/- 72.08
+      value: 138.92 +/- 113.54
       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': 5000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1682858599.b4fa2209992c.2562.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f66b20c6279158e2d32585db67b8a191ea8f4b84bd196b326deda8a0adb61f4
+size 6741671

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a363dfe098933c96feb65ea5062a91e8aacf7448c05ac211c1404fb4e0f78d9
+oid sha256:fcdefaa7f881c029aeb49734fea31a760b8daff9c4b5bbf52eadffc7fbe6e3ea
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -128.30442400021101, "std_reward": 72.08388795156573, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-30T10:27:28.683895"}
+{"env_id": "LunarLander-v2", "mean_reward": 138.91669271348144, "std_reward": 113.53913172947466, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-30T14:33:11.425843"}