Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -126.42 +/- 50.91
+      value: 49.07 +/- 67.28
       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.1677677564.218c4c1a453f.5337.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2021890e512e41a748d3bb363b7abcc3c8d0a2d4f50cc68c40a81038d7a2885e
+size 659817

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3262cb9f8d71762568958150de91d2adbb7385c87e56d48030e8005230aa5d95
+oid sha256:a9f46f0c7b70f362e72eed22c3293e3d84fecfb7f3a67337d95096ecff1763a0
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -126.42498626636412, "std_reward": 50.909285459635356, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-01T13:31:56.835315"}
+{"env_id": "LunarLander-v2", "mean_reward": 49.07028470248496, "std_reward": 67.28415036110147, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-01T13:47:09.575729"}