In this paper we discuss a number of previously unaddressed issues that arise in automated negotiation among self-interested agents whose rationality is bounded by computational complexity. These issues are presented in the context of iterative task allocation negotiations. First, the reasons why such agents need to be able to choose the stage and level of commitment dynamically are identified. A protocol that allows such choices through conditional commitment breaking penalties is presented. Next, the implications of bounded rationality are analyzed. Several tradeoffs between allocated computation and negotiation benefits and risk are enumerated, and the necessity of explicit local deliberation control is substantiated. Techniques for linking negotiation items and multiagent contracts are presented as methods for escaping local optima in the task allocation process. Implementing both methods among self-interested bounded rational agents is discussed. Finally, the ...

This paper analyzes coalitions among self-interested agents that need to solve combinatorial optimization problems to operate e ciently in the world. By colluding (coordinating their actions by solving a joint optimization prob-lem) the agents can sometimes save costs compared to operating individually. A model of bounded rationality is adopted where computation resources are costly. It is not worthwhile solving the problems optimally: solution quality is decision-theoretically traded o against computation cost. A normative, application- and protocol-independent theory of coalitions among bounded-rational agents is devised. The optimal coalition structure and its stability are signi cantly a ected by the agents ' algorithms ' performance pro les and the cost of computation. This relationship is rst analyzed theoretically. Then a domain classi cation including rational and bounded-rational agents is in-troduced. Experimental results are presented in vehicle routing with real data from ve dispatch centers. This problem is NP-complete and the instances are so large that|with current technology|any agent's rationality is bounded by computational complexity. 1

In this paper we outline a general approach to the study of metareasoning, not in the sense of explicating the semantics of explicitly specified meta-level control policies, but in the sense of providing a basis for selecting and justifying computational actions. This research contributes to a developing attack on the problem of resource-bounded rationality, by providing a means for analysing and generating optimal computational strategies. Because reasoning about a computation without doing it necessarily involves uncertainty as to its outcome, probability and decision theory will be our main tools. We develop a general formula for the utility of computations, this utility being derived directly from the ability of computations to affect an agent's external actions. We address some philosophical difficulties that arise in specifying this formula, given our assumption of limited rationality. We also describe a methodology for applying the theory to particular problem-solving systems, a...

A Dissertation Presented by TUOMAS W. SANDHOLM

Abstract not found

Since its inception, artificial intelligence has relied upon a theoretical foundation centred around perfect rationality as the desired property of intelligent systems. We argue, as others have done, that this foundation is inadequate because it imposes fundamentally unsatisfiable requirements. As a result, there has arisen a wide gap between theory and practice in AI, hindering progress in the field. We propose instead a property called bounded optimality. Roughly speaking, an agent is bounded-optimal if its program is a solution to the constrained optimization problem presented by its architecture and the task environment. We show how to construct agents with this property for a simple class of machine architectures in a broad class of real-time environments. We illustrate these results using a simple model of an automated mail sorting facility. We also define a weaker property, asymptotic bounded optimality (ABO), that generalizes the notion of optimality in classical complexity th...

The long-term goal of our field is the creation and understanding of intelligence. Productive research in AI, both practical and theoretical, benefits from a notion of intelligence that is precise enough to allow the cumulative development of robust systems and general results. This paper outlines a gradual evolution in our formal conception of intelligence that brings it closer to our informal conception and simultaneously reduces the gap between theory and practice. 1 Artificial Intelligence AI is a field in which the ultimate goal has often been somewhat ill-defined and subject to dispute. Some researchers aim to emulate human cognition, others aim at the creation of

This paper analyzes coalition formation among self-interested agents that need to solve combinatorial optimization problems to operate efficiently in the world. By colluding (coordinating their actions by solving a joint optimization problem), the agents can sometimes save costs compared to operating individually. A model of bounded rationality is adopted, where computation resources are costly. It is not worth solving the problems optimally: solution quality is decision-theoretically traded off against computation cost. A normative theory of coalitions among bounded rational (BR) agents is devised. The optimal coalition structure and its stability are significantly affected by the agents ' algorithms ' performance profiles (PPs) and the cost of computation. This relationship is first analyzed theoretically. A domain classification including rational and BR agents is introduced. Experimental results are presented in the distributed vehicle routing domain using real data from 5 dispatch centers; the optimal coalition structure for BR agents differs significantly from the one for rational agents. These problems are NP-complete and the instances are so large that, with current technology, any agent's rationality is bounded by computational complexity. 1

A program is bounded optimal for a given computational device for a given environment, if the expected utility of the program running on the device in the environment is at least as high as that of all other programs for the device. Bounded optimality differs from the decision-theoretic notion of rationality in that it explicitly allows for the finite computational resources of real agents. It is thus a central issue in the foundations of artificial intelligence. In this paper we consider a restricted class of agent architectures, in which a program consists of a sequence of decision procedures generated by a learning program or given a priori. For this class of agents, we give an efficient construction algorithm that generates a bounded optimal program for any episodic environment, given a set of training examples. The algorithm includes solutions to a new class of optimization problems, namely scheduling computational processes for real-time environments. This class appears to conta...

We develop a normative theory of interaction---negotiation in particular---among self-interested computationally limited agents where computational actions are game theoretically treated as part of an agent's strategy. We focus on a 2-agent setting where each agent has an intractable individual problem, and there is a potential gain from pooling the problems, giving rise to an intractable joint problem. At any time, an agent can compute to improve its solution to its own problem, its opponent's problem, or the joint problem. At a deadline the agents then decide whether to implement the joint solution, and if so, how to divide its value (or cost). We present a fully normative model for controlling anytime algorithms where each agent has statistical performance profiles which are optimally conditioned on the problem instance as well as on the path of results of the algorithm run so far. Using this model, we introduce a solution concept, which we call deliberation equilibrium. It is the perfect Bayesian equilibrium of the game where deliberation actions are part of each agent's strategy. The equilibria differ based on whether the performance profiles are deterministic or stochastic, whether the deadline is known or not, and whether the proposer is known in advance or not. We present algorithms for finding the equilibria. Finally, we show that there exist instances of the deliberation--bargaining problem where no pure strategy equilibria exist and also instances where the unique equilibrium outcome is not Pareto efficient.