Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -173.25 +/- 101.29
+      value: -149.15 +/- 80.05
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50
+'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1697378618.3eb9289d18f7.10283.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee850c05529406b6944df0b1c737eda000734d89129c0560ddf6c704f32acc50
+size 110089

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e541b1708d23f31c9369b677df43ff11571f22fa1554ebef621b3cc7dae1051e
+oid sha256:1ba9eba95178b8c1eeff91f1866f65cb2c8b1c65ceedc704e4da139555fb0614
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -173.24874476583906, "std_reward": 101.28761803290907, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-15T14:02:53.088523"}
+{"env_id": "LunarLander-v2", "mean_reward": -149.14553802743006, "std_reward": 80.05316891648808, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-15T14:04:21.452201"}