Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -175.89 +/- 137.55
+      value: -138.13 +/- 134.66
       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': 200000
 'learning_rate': 0.0001
 'num_envs': 4
 'num_steps': 256

logs/events.out.tfevents.1689399027.156f3702c70c.18767.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e284b3f04583c820ca03447da46d10d5c89aa8c68734a73e889268b0f956026
+size 324135

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe528db225a277544416c5478a1460cf04a3469338e69e027c3736186fbb37d0
+oid sha256:9e90d59e0b3c02b227000f594d8a356b6d8f0e8a5485ed17b678662a381d1483
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -175.89101428862736, "std_reward": 137.5507385463633, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-15T05:18:09.244044"}
+{"env_id": "LunarLander-v2", "mean_reward": -138.12542515894876, "std_reward": 134.66306978584672, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-15T05:33:15.822866"}