Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -146.53 +/- 52.92
+      value: -118.78 +/- 51.49
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 25000
+'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1677657553.75ced473f136.3000.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:709d7500f5a2866c658c5303b1d1f372e0cb16be672e04b64c5123abe41c42c0
+size 111161

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:500b10200ce0a800529bcedc1ad7e2918578606cb34569750159fa2fe5b22e04
+oid sha256:3262cb9f8d71762568958150de91d2adbb7385c87e56d48030e8005230aa5d95
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -146.52614140763308, "std_reward": 52.9173637352744, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-01T07:58:44.716151"}
+{"env_id": "LunarLander-v2", "mean_reward": -118.7777786677241, "std_reward": 51.48978124873217, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-01T07:59:55.356456"}