We introduce point-based dynamic programming (DP) for decentralized partially observable Markov decision processes (DEC-POMDPs), a new discrete DP algorithm for planning strategie...
Parallel and distributed information processing systems play an increasingly important role in artificial intelligence and computer science. In this article an approach to learnin...
A directed agent implies an agent with high constraints in both recognition and motion. Because of the embodied restrictions, the directed agent perceives a sense of subjective di...
Abstract- Multiagent reinforcement learning for multirobot systems is a challenging issue in both robotics and artificial intelligence. With the ever increasing interests in theor...
In this paper we propose interaction-driven Markov games (IDMGs), a new model for multiagent decision making under uncertainty. IDMGs aim at describing multiagent decision problem...