Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -161.14 +/- 81.23
+      value: -118.18 +/- 45.61
       name: mean_reward
       verified: false
 ---
@@ -32,7 +32,7 @@ model-index:
 'gym_id': 'LunarLander-v2'
 'seed': 1
 'learning_rate': 0.00025
-'total_timesteps': 25000
+'total_timesteps': 50000
 'torch_deterministic': True
 'cuda': True
 'track': False

logs/events.out.tfevents.1742553886.71b7493f9981.2867.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7961010ec59557064edcfa1a19105c3701737595704c5ce202e4a32d6203822c
+size 109732

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69fb27f411b06eff122c6749da83d0e9591e95cd25a4ffb58729bb951747ee69
+oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
 size 43026

results.json

@@ -1 +1 @@
-{"gym_id": "LunarLander-v2", "mean_reward": -161.13778571690048, "std_reward": 81.23247839090567, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-21T10:41:07.398411"}
+{"gym_id": "LunarLander-v2", "mean_reward": -118.1845399963513, "std_reward": 45.60931032008683, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-21T10:45:28.454741"}