Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -220.61 +/- 116.23
+      value: -148.56 +/- 78.86
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 1000000
 'learning_rate': 0.0003
 'num_envs': 16
 'num_steps': 1024

logs/events.out.tfevents.1703783537.68fce4a30bf5.3684.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98159e56b721d7bdea82011ee2d97cfab2650db2aa8b4e40545b61cf11560a57
+size 1114865

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7580f79664e0fbd43f40634ef542e298fca0d1ae1da8e848b0a820aabd7e8b05
+oid sha256:788f1b6854532082b9fdc6b003e92bd0d9717c9361e94e8c25ddd52a49326903
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -220.6070337968803, "std_reward": 116.23288124835211, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-28T17:11:16.373540"}
+{"env_id": "LunarLander-v2", "mean_reward": -148.5643349645792, "std_reward": 78.86251503512707, "n_evaluation_episodes": 10, "eval_datetime": "2023-12-28T17:17:45.291708"}