Communication decisions in multi-agent cooperation

Xuan, Ping; Lesser, Victor; Zilberstein, Shlomo

doi:10.1145/375735.376469

Cited by 141 publications

(105 citation statements)

References 11 publications

Supporting

Mentioning

103

Contrasting

Unclassified

Order By: Relevance

“…The emerging field of distributed POMDPs [3,4,30,43,29,16] provides a rich framework for modeling uncertainties and utilities in complex multiagent domains. However, as shown by Bernstein et al [3], the problem of deriving the optimal policy is computationally intractable.…”

Section: Resultsmentioning

confidence: 99%

“…In contrast to BDI systems introduced in the previous section, RMTDP enables explicit quantitative optimization of team performance. Note that, while we use MTDP, other possible distributed POMDP models could potentially also serve as a basis [3,43].…”

Section: Role-based Multiagent Team Decision Problemmentioning

confidence: 99%

“…Unfortunately, we cannot directly use single-agent POMDP techniques [20] for maintaining or updating belief states [20] in a MTDP -unlike in a single agent POMDP, in MTDP, an agent's observation depends not only on its own actions, but also on unknown actions of other agents. Thus, as with other distributed POMDP models [3,43], in MTDP, local policies π i are indexed by observation histories. π =< π 1 , .…”

Section: Multiagent Team Decision Problemmentioning

confidence: 99%

“…Fortunately, the emergence of distributed Partially Observable Markov Decision Problems (POMDPs) provides models [3,4,30,43] that are well-suited for quantitative analysis of agent teams in uncertain domains. These models are powerful enough to express the uncertainty in these dynamic domains and in principle, can be used to generate and evaluate complete policies for the multiagent team.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Coordinating Teams in Uncertain Environments: A Hybrid BDI-POMDP Approach

Nair

Tambe

2005

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Distributed partially observable Markov decision problems (POMDPs) have emerged as a popular decision-theoretic approach for planning for multiagent teams, where it is imperative for the agents to be able to reason about the rewards (and costs) for their actions in the presence of uncertainty. However, finding the optimal distributed POMDP policy is computationally intractable (NEXPComplete). This paper is focussed on a principled way to combine the two dominant paradigms for building multiagent team plans, namely the "belief-desireintention" (BDI) approach and distributed POMDPs. In this hybrid BDI-POMDP approach, BDI team plans are exploited to improve distributed POMDP tractability and distributed POMDP-based analysis improves BDI team plan performance. Concretely, we focus on role allocation, a fundamental problem in BDI teams -which agents to allocate to the different roles in the team. The hybrid BDI-POMDP approach provides three key contributions. First, unlike prior work in multiagent role allocation, we describe a role allocation technique that takes into account future uncertainties in the domain. The second contribution is a novel decomposition technique, which exploits the structure in the BDI team plans to significantly prune the search space of combinatorially many role allocations. Our third key contribution is a significantly faster policy evaluation algorithm suited for our BDI-POMDP hybrid approach. Finally, we also present experimental results from two domains: mission rehearsal simulation and RoboCupRescue disaster rescue simulation. In the RoboCupRescue domain, we show that the role allocation technique presented in this paper is capable of performing at human expert levels by comparing with the allocations chosen by humans in the actual RoboCupRescue simulation environment.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Role-based Multiagent Team Decision Problemmentioning

confidence: 99%

Section: Multiagent Team Decision Problemmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Coordinating Teams in Uncertain Environments: A Hybrid BDI-POMDP Approach

Nair

Tambe

2005

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Recent attempts identify different classes of multi-robot decision process that include Multi-Agent Markov Decision Process (MMDP) proposed by Boutilier [Bou99], the Partial Observable Identical Payoff Stochastic Game (POIPSG) proposed by Peshkin et al [PKMK00], the multi-agent decision process by Xuan and Lesser [XLZ00], the Communicative Multiagent Team Decision Problem (COM-MTDP) proposed by Pynadath and Tambe [NPY + 03], the Decentralized Markov Decision Process (DEC-POMDP and DEC-MDP) by Bernstein et al [BZI00], DEC-MDP with a central coordination proposed by Hanna and Mouaddib [HM02], the DEC-POMDP with communication proposed by Goldman and Zilberstein [GZ03] and Transition Independent DEC-MDP proposed by Becker et al [BZLG03]. Bererton et al [BGT03] present an extension of MDPs and apply auction mechanisms to coordinate multiple robots.…”

Section: Introductionmentioning

confidence: 99%