Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -148.80 +/- 62.20
+      value: -30.78 +/- 17.30
       name: mean_reward
       verified: false
 ---
@@ -32,7 +32,7 @@ model-index:
 'gym_id': 'LunarLander-v2'
 'learning_rate': 0.00025
 'seed': 1
-'total_timesteps': 50000
+'total_timesteps': 500000
 'torch_deterministic': True
 'cuda': True
 'track': False

logs/events.out.tfevents.1708312984.387b54f45cea.14831.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06318a3243cdc6199c611601ee99bb65f26af8f12bb51437d2933ee5b748c154
+size 676748

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d75351e894214829ae114d6c7a39117992663cf360c4b8ec87d3dd9d599ddd01
+oid sha256:5cd129df90a2e144ffc781d0d01e0566a551ad129c94f45a8ee98a1d250804f2
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -148.79812857391465, "std_reward": 62.203591166642866, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-19T03:22:02.374851"}
+{"env_id": "LunarLander-v2", "mean_reward": -30.777002924990676, "std_reward": 17.296541448559843, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-19T03:38:01.800776"}