Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
  type: LunarLander-v2
  metrics:
  - type: mean_reward
- value: 232.34 +/- 34.97
+ value: 252.98 +/- 69.66
  name: mean_reward
  verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 5000000
+'total_timesteps': 10000000
 'learning_rate': 0.00025
 'num_envs': 16
 'num_steps': 1024

logs/events.out.tfevents.1692249578.muon.54982.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a58d76e27c499d374e20dde5cd915976e97e2e690ac8502eb9f7149c371d218
+size 3274870

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0576f3ff5bb509eefd80d3dcc5ad30b21044fa6d31bab7a742b6a4eef8d381b
+oid sha256:50d991ef270ca717723b3f83e40ed17f54daa34f4b6f330f5c36ab60d3a32b58
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 232.33544682323776, "std_reward": 34.972575398336566, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-16T22:13:46.510058"}
+{"env_id": "LunarLander-v2", "mean_reward": 252.9774163468425, "std_reward": 69.65976185058726, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-16T23:03:34.722769"}