Tangamchit, Poj Dolan, John Khosla, Pradeep The Necessity of Average Rewards in Cooperative Multirobot Learning <p> </p><p>Learning can be an effective way for robot systems to deal with dynamic environments and changing task conditions. However, popular single-robot learning algorithms based on discounted rewards, such as Q learning, do not achieve cooperation (i.e., purposeful division of labor) when applied to task-level multirobot systems. A task-level system is defined as one performing a mission that is decomposed into subtasks shared among robots. In this paper, we demonstrate the superiority of average-reward-based learning such as the Monte Carlo algorithm for task-level multirobot systems, and suggest an explanation for this superiority.</p> <p></p> Software Research 2002-01-01
    https://kilthub.cmu.edu/articles/journal_contribution/The_Necessity_of_Average_Rewards_in_Cooperative_Multirobot_Learning/6626153
10.1184/R1/6626153.v1