Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 109.63 +/- 119.39
+      value: 170.94 +/- 111.29
       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': 800000
 'learning_rate': 0.0002
 'num_envs': 4
 'num_steps': 256

logs/events.out.tfevents.1710911635.78f44feafe37.29970.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72fcf14672951b46ba8f2c181d6e94ea34ec32d0a02b817c6732fb3145c48006
+size 700395

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49469b9e42459f7489b52597d507daaea1a9bfa2f099094c278179509d0daee5
+oid sha256:f15ceac5dc9c828dbfaf2d43999768cf0708dd6a1e69c18f9af2637602bf45ee
 size 111402

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 109.62536445227552, "std_reward": 119.39185550969252, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-20T04:58:03.093789"}
+{"env_id": "LunarLander-v2", "mean_reward": 170.94232489360652, "std_reward": 111.29491466674651, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-20T05:31:59.650198"}