Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -107.83 +/- 61.67
+      value: -155.36 +/- 103.91
       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': 60000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1710076595.Burak.18772.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bdc8c4b5f2b31bbc9ef5283d0860ab5c615579135a6a607dac8ede6b6fbea28
+size 136630

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e4d1aca826a59077b3ad15d798ce963b9dabedf303b62057fdbef05dfaa22e3
+oid sha256:11069ecff64ff3910d1fe20e78e9d4e16089f15a0aac275915139429e676173e
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -107.82914156394625, "std_reward": 61.67123004334045, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-10T16:08:04.072825"}
+{"env_id": "LunarLander-v2", "mean_reward": -155.35559860186441, "std_reward": 103.91490348467143, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-10T16:18:14.704824"}