List your company
ResearchFormerly WizWand

Restless Multi-Armed Bandit Scheduling on 1-D Bandit

957Regret (Reg(T))SW-Whittle
-617.2810,009.1120,635.531,261.89Jun 22, 2025
Updated 6mo ago

Evaluation results

MethodLinks
SW-Whittle(N, M)=(10, 1)2025.06957
SW-Whittle(N, M)=(20, 4)2025.062,065
SW-Whittle(N, M)=(10, 4)2025.062,119
UCWhittle+Win(N, M)=(10, 1)2025.066,377
UCWhittle(N, M)=(10, 1)2025.066,528
Random(N, M)=(10, 1)2025.0611,916
WIQL(N, M)=(10, 1)2025.0612,060
UCWhittle+Win(N, M)=(10, 4)2025.0621,628
UCWhittle+Win(N, M)=(20, 4)2025.0624,405
UCWhittle(N, M)=(10, 4)2025.0627,620
WIQL(N, M)=(10, 4)2025.0628,068
Random(N, M)=(10, 4)2025.0628,349
UCWhittle(N, M)=(20, 4)2025.0628,985
Random(N, M)=(20, 4)2025.0639,358
WIQL(N, M)=(20, 4)2025.0640,314