Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -180.06 +/- 101.13
+      value: -14.33 +/- 85.34
       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.1727356142.70c6f8ef8334.4524.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7289c34b0354ad7bb8be1f8130e9c4ba2c7f6880fd39a8e594214d88181c458c
+size 675361

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
+oid sha256:c92c631e7b978acf25a81dd9a83a3caf08de2979f0ea9b1370f6a8fc6e2143ec
 size 43026

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bba36351f2b4c2620f10e5504a133cda93916b7016c5a6d288e21a0796c98e6
-size 19419
+oid sha256:8eeafe8b577e87891549d8e3f750e79b1522e7a390630159774e95fca4603fe3
+size 195824

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -180.0636013297672, "std_reward": 101.13174976125232, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-26T13:05:09.508664"}
+{"env_id": "LunarLander-v2", "mean_reward": -14.32569953203776, "std_reward": 85.34158094988845, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-26T13:23:15.712117"}