Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -160.76 +/- 76.31
+      value: -59.21 +/- 64.24
       name: mean_reward
       verified: false
 ---
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
-'learning_rate': 0.00025
+'total_timesteps': 500000
+'learning_rate': 0.0001
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1683324784.ef0df3ebac95.10765.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bab336bd24ace70769040f23688b012310150e074ed4c82562f45783d26416f
+size 720120

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a363dfe098933c96feb65ea5062a91e8aacf7448c05ac211c1404fb4e0f78d9
+oid sha256:9ee0f659ecb3e4404cab33908684814d212ecd677a4f843c277d1c42846219fb
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -160.76394418924957, "std_reward": 76.30826726296678, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-05T22:07:27.631285"}
+{"env_id": "LunarLander-v2", "mean_reward": -59.21020785878295, "std_reward": 64.23542763948329, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-05T22:25:03.310226"}