Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 5.68 +/- 73.75
+      value: 122.70 +/- 117.96
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 500000
+'total_timesteps': 5000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1692664879.79e47a386354.8771.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a651da4e296d1d598c59d2047acc16349bfe5999b91427dc3e6bd8cbfd1afff6
+size 7114218

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95d2db815a33646e84e478628a4da4f156c95480a7b55276eebdc219ec4fcd18
+oid sha256:5b3dae2e8f99a76fb721428b13d88122e6247c22b8b1df83a193a762625ee796
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 5.6751323308812776, "std_reward": 73.74990066377366, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-22T00:32:24.958608"}
+{"env_id": "LunarLander-v2", "mean_reward": 122.70420152209167, "std_reward": 117.95623745795997, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-22T02:12:37.443856"}