Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -140.26 +/- 15.43
+      value: 150.08 +/- 50.42
       name: mean_reward
       verified: false
 ---
@@ -31,7 +31,7 @@ model-index:
   {'exp_name': 'ppo'
 'env_id': 'LunarLander-v2'
 'seed': 1
-'total_timesteps': 1000
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'anneal_lr': True
 'gae': True

logs/events.out.tfevents.1693674167.7ec8f7432e8a.4015.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:846fd08b94735bd43d14d967db45abbe8c7621d113e0861430a86b03ea109935
+size 11781785

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba52f22dda563c21ed5e710e96a07eea3483a953f3f885dfc2e3d75a43518155
+oid sha256:e3dfe8fe39cae5052218ebeda80959212044155dcc4285d48e51d20eb424c3c8
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -140.25682817856529, "std_reward": 15.433371255764742, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-02T16:59:21.087273"}
+{"env_id": "LunarLander-v2", "mean_reward": 150.08267646104653, "std_reward": 50.423076453560384, "n_evaluation_episodes": 10, "eval_datetime": "2023-09-02T17:41:24.457679"}