Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -174.28 +/- 81.21
+      value: -129.27 +/- 83.17
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 5
+'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1678314945.daniels-mbp.lan.61381.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2949104bade49b062b83c0c006521344b106399c38e38482059476ec0df229e
+size 111708

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6d8732acdf648c4e3e9b981bf4647bd131b50baa5ab232f165f66d2cb1ccff0
+oid sha256:9fdb012b10459ef3582d5f5d283c67bb54fbfb3fe0c6eefda325f33b9b7e2683
 size 42689

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -174.27960497360036, "std_reward": 81.21288016955556, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-08T17:34:04.148072"}
+{"env_id": "LunarLander-v2", "mean_reward": -129.27253730035565, "std_reward": 83.17099559615481, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-08T17:36:20.064744"}