Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -190.67 +/- 121.47
+      value: -3.93 +/- 95.19
       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.1722839016.6372f63c7d88.23797.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09c31b6e6d1427d1deadff485e820e07bf9987b0e9597b04fe85fe9902ab2b7b
+size 503083

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:262f0a9e7dedc62f7f9e3ea03fd61b3fc9c3a0ea691c3faed672ba65a915e277
+oid sha256:fd1bee2e8f5e0b803eac5ce02d04b9c4496773a9048a77c341fc99abe5209d40
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -190.6740590844976, "std_reward": 121.46837629994836, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-05T06:22:48.389706"}
+{"env_id": "LunarLander-v2", "mean_reward": -3.9259596087702726, "std_reward": 95.1896291467059, "n_evaluation_episodes": 10, "eval_datetime": "2024-08-05T06:37:28.671853"}