Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -14.30 +/- 118.45
+      value: 59.97 +/- 135.06
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 500000
+'total_timesteps': 250000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1677178640.a4105b5668f5.18536.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30585d88be56fc772e982df0eaf62ef6e2f44303f83730b9a5787680d57357d2
+size 346547

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:654525486d95e217230ea42d3da0627dd8db78a65329581a2953711a8d8a8c67
+oid sha256:46651a4f38fca36a0dea579b2d2be4a6551e54c2f828cb22d54a0bd0bafd6c2a
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -14.302093163783747, "std_reward": 118.44641372830634, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-23T18:54:50.076481"}
+{"env_id": "LunarLander-v2", "mean_reward": 59.970445023307, "std_reward": 135.0613036098908, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-23T19:05:00.966572"}