The paper explores a very simple agent design method called Q-decomposition, wherein a complex agent is built from simpler subagents. Each subagent has its own reward function and...
We examine the problem of Transfer in Reinforcement Learning and present a method to utilize knowledge acquired in one Markov Decision Process (MDP) to bootstrap learning in a mor...
We present new algorithms for inverse optimal control (or inverse reinforcement learning, IRL) within the framework of linearlysolvable MDPs (LMDPs). Unlike most prior IRL algorit...
Much emphasis in multiagent reinforcement learning (MARL) research is placed on ensuring that MARL algorithms (eventually) converge to desirable equilibria. As in standard reinfor...
Abstract. Many reinforcement learning domains are highly relational. While traditional temporal-difference methods can be applied to these domains, they are limited in their capaci...
Trevor Walker, Lisa Torrey, Jude W. Shavlik, Richa...