Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -142.58 +/- 63.60
+      value: -131.13 +/- 79.07
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 1000000
 'learning_rate': 2.5e-05
 'num_envs': 12
 'num_steps': 128

logs/events.out.tfevents.1676773420.5e7fcccfc678.4577.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b676bc5bf1ce5c0a97ef29938ba7f913ecbf2cc59d8ba4946afd3034723a481a
+size 1427738

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec50c094714203054e4da9f0499b48c992eb2cbabc15dcee46ddaac3b56d34af
+oid sha256:7cd4b85914899feb9d2bbeef24aca091a6ac6bc11c04b585454d2908bfea22e8
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -142.57921862519373, "std_reward": 63.604505800627514, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T02:23:02.320757"}
+{"env_id": "LunarLander-v2", "mean_reward": -131.13230129684894, "std_reward": 79.06856915869395, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T02:31:13.899828"}