Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -179.75 +/- 132.02
+      value: -59.24 +/- 99.08
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1768284660.MSI.41088.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d91e0ff7b8ecb8f79ecb972c7f3d37e0d814a3199ef1548f39a4457b955cefa
+size 1006251

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b87923422514ca797ce8bb7fb9ba2ec993b327d3c5778d4a0d0fa15fe24ac456
+oid sha256:2fcd96de5d8a1dd060420fd32a4b3241d0ab12114afacf781c3bffac0e3b6aa5
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -179.7460306594173, "std_reward": 132.0195495026761, "n_evaluation_episodes": 10, "eval_datetime": "2026-01-13T11:39:30.544774"}
+{"env_id": "LunarLander-v2", "mean_reward": -59.23984562973768, "std_reward": 99.08325791639184, "n_evaluation_episodes": 10, "eval_datetime": "2026-01-13T12:11:12.970574"}