Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -109.02 +/- 35.48
+      value: 57.03 +/- 121.77
       name: mean_reward
       verified: false
 ---
@@ -32,7 +32,7 @@ model-index:
 'gym_id': 'LunarLander-v2'
 'learning_rate': 0.00025
 'seed': 1
-'total_timesteps': 100000
+'total_timesteps': 1000000
 'torch_deterministic': True
 'cuda': True
 'capture_video': False

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc26766cac9746ca12249c4fb443206f48d5f3c54eb85d6afeeccc4090caf90b
+oid sha256:b2ae916c1b775861dfaae073559847ff305bdd0649b35a0f19920a94028ae9f4
 size 42469

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -109.02344514711778, "std_reward": 35.47524274053103, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-21T21:45:06.655859"}
+{"env_id": "LunarLander-v2", "mean_reward": 57.02606244717896, "std_reward": 121.76941602249677, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-21T21:52:55.283822"}