Between collaboration and competition : An Initial Formalization using Distributed POMDPs

ABSTRACT This paper presents an initial formalization of teamwork in multi-agent domains. Although analyses of teamwork already exist in the literature of multi-agent systems, almost no work has dealt with the problem of teams that comprise self-interested agents. The main contribution of this work is that it concentrates speci cally on such teams of self interested agents. Teams of this kind are common in multi-agent systems as they model the implicit competition between team members that often arises within a team. Our work models the internal struggle of agents that are acting in a team as they try to maximise their individual payo while at the same time acting in a manner that is bene cial to the entire team. This dilemma of self interest versus team interest is a problem that has been studied in game and decision making theory, although no clear-cut solution that applies to agent systems has been proposed. Our formalisation is based on the theory of Partially Observable Markov Decision Processes (POMDPs). In this work, we reintroduce and extend the Electric Elves (EElves), an application of personal assistant agents that displays all the characteristics of competition within a cooperative setting. Using E-Elves we show how competition arises out of a collaborative scenario and analyse the shortcomings of previous approaches in handling this competition. Finally, we provide some initial thoughts on how to cope with these problems based on our previous experience with E-Elves.

[1]  Leslie Pack Kaelbling,et al.  Planning and Acting in Partially Observable Stochastic Domains , 1998, Artif. Intell..

[2]  Katia P. Sycara,et al.  Coordination of Multiple Intelligent Software Agents , 1996, Int. J. Cooperative Inf. Syst..

[3]  E. Rasmusen Moral Hazard in Risk-Averse Teams , 1987 .

[4]  Milind Tambe,et al.  The Communicative Multiagent Team Decision Problem: Analyzing Teamwork Theories and Models , 2011, J. Artif. Intell. Res..

[5]  F. Kramarz,et al.  Dynamic focal points in N-person coordination games , 1996 .

[6]  V. Crawford,et al.  Learning How to Cooperate: Optimal Play in Repeated Coordination Games , 1990 .

[7]  John. Moore,et al.  Stopping agents from “cheating” , 1988 .

[8]  Sarit Kraus,et al.  Collaborative Plans for Complex Group Action , 1996, Artif. Intell..

[9]  Piotr J. Gmytrasiewicz,et al.  Formalizing multi-agent POMDP's in the context of network routing , 2003, 36th Annual Hawaii International Conference on System Sciences, 2003. Proceedings of the.

[10]  John C. Harsanyi,et al.  Общая теория выбора равновесия в играх / A General Theory of Equilibrium Selection in Games , 1989 .

[11]  V Bhaskar Breaking the Symmetry: Optimal Conventions in Repeated Symmetric Games , 1997 .

[12]  Sarit Kraus,et al.  The influence of social norms and social consciousness on intention reconciliation , 2002, Artif. Intell..

[13]  Jean Oh,et al.  Electric Elves: Immersing an Agent Organization in a Human Organization , 2000 .

[14]  H. Young,et al.  The Evolution of Conventions , 1993 .

[15]  Milind Tambe,et al.  Towards Adjustable Autonomy for the Real World , 2002, J. Artif. Intell. Res..

[16]  Bengt Holmstrom,et al.  Moral Hazard in Teams , 1982 .

[17]  C. Ma Unique Implementation of Incentive Contracts with Many Agents , 1988 .

[18]  Milind Tambe,et al.  Role allocation and reallocation in multiagent teams: towards a practical analysis , 2003, AAMAS '03.

[19]  Jean Oh,et al.  Electric Elves: Agent Technology for Supporting Human Organizations , 2002, AI Mag..

[20]  Anindya Banerjee,et al.  Efficiency in hierarchies: implementing the first-best solution by sequential actions , 1989 .

[21]  Daphne Koller,et al.  Multi-agent algorithms for solving graphical games , 2002, AAAI/IAAI.

[22]  Robert Forsythe,et al.  Selection Criteria in Coordination Games: Some Experimental Results , 1987 .

[23]  S. Thrun,et al.  Game-Theoretic Communication Policies for Partially Observable Markov Games , 2022 .

[24]  R. Rob,et al.  Learning, Mutation, and Long Run Equilibria in Games , 1993 .

[25]  Dilip Mookherjee Optimal Incentive Schemes with Many Agents , 1984 .

[26]  Jean Oh,et al.  Electric Elves: Applying Agent Technology to Support Human Organizations , 2001, IAAI.

[27]  Milind Tambe,et al.  Multiagent teamwork: analyzing the optimality and complexity of key theories and models , 2002, AAMAS '02.

[28]  Bart Selman,et al.  An Experiment in the Design of Software Agents , 1994, AAAI.

[29]  A. Rubinstein,et al.  Games with Procedurally Rational Players , 1997 .

[30]  J. Huyck,et al.  Tacit Coordination Games, Strategic Uncertainty, and Coordination Failure , 1990 .