The Communicative Multiagent Team Decision Problem: Analyzing Teamwork Theories and Models

TLDR

Despite progress in multiagent teamwork, research has not examined the tradeoffs between optimality and complexity, leaving it unclear whether the efficiency gains of existing theories justify performance losses. The authors present the COM‑MTDP framework to evaluate these optimality–complexity tradeoffs and to provide a foundation for developing new team coordination algorithms. COM‑MTDP extends decentralized partially observable Markov decision processes and economic team theory, enabling analysis of optimal team performance and computational complexity across observability and communication cost dimensions while encoding joint intentions theory instantiations. They derive a domain‑independent optimal communication criterion, compare two joint intentions instantiations under this criterion, and implement a reusable software package that demonstrates the analysis in an example domain.

Abstract

Despite the significant progress in multiagent teamwork, existing research does not address the optimality of its prescriptions nor the complexity of the teamwork problem. Without a characterization of the optimality-complexity tradeoffs, it is impossible to determine whether the assumptions and approximations made by a particular theory gain enough efficiency to justify the losses in overall performance. To provide a tool for use by multiagent researchers in evaluating this tradeoff, we present a unified framework, the COMmunicative Multiagent Team Decision Problem (COM-MTDP). The COM-MTDP model combines and extends existing multiagent theories, such as decentralized partially observable Markov decision processes and economic team theory. In addition to their generality of representation, COM-MTDPs also support the analysis of both the optimality of team performance and the computational complexity of the agents' decision problem. In analyzing complexity, we present a breakdown of the computational complexity of constructing optimal teams under various classes of problem domains, along the dimensions of observability and communication cost. In analyzing optimality, we exploit the COM-MTDP's ability to encode existing teamwork theories and models to encode two instantiations of joint intentions theory taken from the literature. Furthermore, the COM-MTDP model provides a basis for the development of novel team coordination algorithms. We derive a domain-independent criterion for optimal communication and provide a comparative analysis of the two joint intentions instantiations with respect to this optimal policy. We have implemented a reusable, domain-independent software package based on COM-MTDPs to analyze teamwork coordination strategies, and we demonstrate its use by encoding and evaluating the two joint intentions strategies within an example domain.