Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -17.70 +/- 98.07
+      value: -1.76 +/- 104.38
       name: mean_reward
       verified: false
 ---
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000000
-'learning_rate': 0.00024
+'total_timesteps': 500000
+'learning_rate': 0.001
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1677147118.17a49215cfb3.29080.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:168cd7f7c62058dddcea57cece29bfe50de6e7068304d7eb02142341b39115d3
+size 634094

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ac7d0e943d40d9266e4a2d3395c31a6a2a8a0bd2f7595bb670b28cdc75d86fa
+oid sha256:22de9f781102e4cd73e29b3938bc1c787302795224126a14ba6b562c9da514be
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -17.69624911991853, "std_reward": 98.07385749764175, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-23T09:53:39.846713"}
+{"env_id": "LunarLander-v2", "mean_reward": -1.7606585136442887, "std_reward": 104.38487287564344, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-23T10:24:55.752793"}