Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -142.35 +/- 52.39
+      value: -190.40 +/- 112.25
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 250000
+'total_timesteps': 500000
 'learning_rate': 1e-05
 'num_envs': 16
 'num_steps': 128
@@ -46,7 +46,7 @@ model-index:
 'gamma': 0.99
 'gae_lambda': 0.95
 'num_minibatches': 4
-'update_epochs': 4
+'update_epochs': 8
 'norm_adv': True
 'clip_coef': 0.2
 'clip_vloss': True

logs/events.out.tfevents.1684423840.irow-pc.67243.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d3ede7075f92ccbe7b717b57530614e4479bd3746574e7628d36c8416afbb03
+size 725572

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6e8269fcf8e64e1962fd0606e566b38e3cb6d84e1595d86d31173fe45b93bd7
+oid sha256:6d3f34fe5c36ba6ca6cfe7e3258e34363e20056bea6b53d2dc0c1037d0fae87c
 size 42817

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -142.34720310087874, "std_reward": 52.38909631768608, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-18T09:27:40.667503"}
+{"env_id": "LunarLander-v2", "mean_reward": -190.39561431334616, "std_reward": 112.2539991590456, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-18T09:32:40.498406"}