T oyota T e hnolo gi al Institute at Chi ago 1427 East 60th Str e et, Chi ago IL, 60637 USA Abstra t Au tions are b e oming an in reasingly p opular metho d for transa ting business, esp e-ially o v er the In ternet. This arti le presen ts a general approa h to building autonomous bidding agen ts to bid in m ultiple sim ultaneous au tions for in tera ting go o ds. A ore omp onen t of our approa h learns a mo del of the empiri al pri e dynami s based on past data and uses the mo del to analyti ally al ulate, to the greatest exten t p ossible, optimal bids. W e in tro du e a new and general b o osting-based algorithm for onditional densit y estimation problems of this kind, i.e., sup ervised learning problems in whi h the goal is to estimate the en tire onditional distribution of the real-v alued lab el. This approa h is fully implemen ted as A TT a -2001, a tops oring agen t in the se ond T rading Agen t Comp etition (T A C-01). In an au tion for a single go o d, it is straigh tforw ...

Pla y ers parti ipating in su h games m ust learn to o ordinate with ea h other in order to re eiv e the highest-p ossible v alue. A n um b er of reinfor emen t learning algorithms ha v e b een prop osed for this problem, and some ha v e b een sho wn to on v erge to go o d solutions in the limit. In this pap er w e sho w that using v ery simple mo del-based algorithms, m u h b etter (i.e., p olynomial) on v ergen e rates an b e attained. Moreo v er, our mo del-based algorithms are guaran teed to on v erge to the optimal v alue, unlik e man y of the existing algorithms. The distributed nature of su h systems mak es the problem of learning to a t in an unkno wn en vironmen t more diÆ ult b e ause the agen ts m ust o ordinate b oth their learning pro ess and their a tion hoi es. Ho w ev er, the need to o ordinate is not restri ted to distributed agen ts, as it arises naturally among self-in terested agen ts in ertain en vironmen ts. A go o d mo del for su h en vironmen ts is that of a ommon-inter est sto hasti game (CISG). A sto hasti game (Shapley, 1953) is a mo del of m ulti-agen t in tera tions onsisting of m ultiple nite or innite stages, in ea h of whi h the agen ts pla y a one-shot strategi form game. The iden tit y of ea h stage dep ends sto hasti ally on the previous stage and the a tions p erformed b y the agen ts in that stage. The goal of ea h agen t is to maximize some fun tion of its rew ard stream - either its a v erage rew ard or its sum of dis oun ted rew ards. A CISG is a sto hasti game in whi h at ea h p oin t the pa y o of all agen ts is iden ti al. V arious algorithms for learning in CISGs ha v e b een prop osed in the literature.

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.

We study the process of multi-agent reinforcement learning in the context ofload balancing in a distributed system, without use of either centralcoordination or explicit communication. We first define a precise frameworkin which to study adaptive load balancing, important features of which are itsstochastic nature and the purely local information available to individualagents. Given this framework, we show illuminating results on the interplaybetween basic adaptive behavior parameters and their effect on systemefficiency. We then investigate the properties of adaptive load balancing inheterogeneous populations, and address the issue of exploration vs.exploitation in that context. Finally, we show that naive use ofcommunication may not improve, and might even harm system efficiency.