Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -118.78 +/- 51.49
+      value: -51.44 +/- 60.03
       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.1677657643.75ced473f136.3434.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2675960f3e5ba07b80fa8a26f3fc41019001983a3e50f77f146c9fe58f17c390
+size 1265025

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3262cb9f8d71762568958150de91d2adbb7385c87e56d48030e8005230aa5d95
+oid sha256:ebb378896b2cb4c43e971f50d7380e681cb99523b73cd341f85c99706c03d9df
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -118.7777786677241, "std_reward": 51.48978124873217, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-01T07:59:55.356456"}
+{"env_id": "LunarLander-v2", "mean_reward": -51.44031462355306, "std_reward": 60.02697446232656, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-01T08:27:46.363971"}