Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -94.97 +/- 47.39
+      value: -157.08 +/- 68.99
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 2.5e-05
+'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1691958079.bcadd1928d08.5532.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ade1d903027a8fbc6f5647e80f6a1e871cb67e48b391e52a86f1de0b9d7b42a1
+size 221308

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24a964bb99c3e3678ce532644be6d567be36cfa8bbc2c58fe698eb533070cb7f
+oid sha256:8802a401f9eedb07ef810eb6d49c91ffd77d753bd96675776004777157abd97e
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -94.96746142704293, "std_reward": 47.39229021896194, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T20:18:07.819868"}
+{"env_id": "LunarLander-v2", "mean_reward": -157.08302744615554, "std_reward": 68.99033468443982, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T20:22:42.142067"}