Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -159.75 +/- 80.39
+      value: -51.99 +/- 22.57
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 0.00025
+'learning_rate': 0.001
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1708096374.ad12a49f4016.8554.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd3b19ad0234a1d562510dc9781fbc1214a161447a57cb4ec449f844b2545a83
+size 152252

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf4a7fde3320b1226867f811244d8c33574eca701ec88ceee90bda5c8724f5d8
+oid sha256:8e89ff43908ce3c0d50220df5f0f51780764df67fee0b39eb3a9db90197daf98
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -159.74735299265723, "std_reward": 80.38856885216012, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-16T15:02:57.216339"}
+{"env_id": "LunarLander-v2", "mean_reward": -51.994895070190765, "std_reward": 22.56652711167145, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-16T15:15:44.124085"}