Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -125.88 +/- 62.88
+      value: 105.02 +/- 94.28
       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.1678702070.195dfc9c372f.4487.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d84b52894de9985e3b980c8033e80bc9a6d33ed6b9187c892c9e3547904e01c
+size 659830

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": -125.87785690772421, "std_reward": 62.87973823505515, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-13T10:00:21.120062"}
+{"env_id": "LunarLander-v2", "mean_reward": 105.01903247623497, "std_reward": 94.28297090161426, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-13T10:22:02.527035"}