Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -213.61 +/- 117.30
+      value: 160.87 +/- 103.90
       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.1707844494.f231eee3a69d.1363.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0119d49086512bb477ec847b39d80b030c7faf1d377d67a381c5137a5d5a76c1
+size 1434207

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e14edb9164048b23bc75d76195f22e5957577187b51bf9fac014e2ebd99a6b2
+oid sha256:4b02bc4ed93554d9fac68cae5417b81474a8ea168a0031d0e31534c39f752859
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -213.60629327444758, "std_reward": 117.29826157210769, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-13T16:36:46.979576"}
+{"env_id": "LunarLander-v2", "mean_reward": 160.86591706788766, "std_reward": 103.90092466616997, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-13T17:36:46.590360"}