arXiv subjects

Jason R. Marden

Publications and source records attributed to Jason R. Marden.

67 records · Page 4Linked to original sources

arXiv2019

Can Taxes Improve Congestion on All Networks?

We ask if it is possible to positively influence social behavior with no risk of unintentionally incentivizing pathological behavior. In network routing problems, if network traffic is composed of many individual agents, it is known that self-interested behavior among the agents can lead to suboptimal network congestion. We study situations in which a system planner charges monetary tolls for the use of network links in an effort to incentivize efficient routing choices by the users, but in which the users' sensitivity to tolls is heterogeneous and unknown. We seek locally-computed tolls that are guaranteed not to incentivize worse network routing than in the un-influenced case. Our main result is to show that if networks are sufficiently complex and populations sufficiently diverse, perverse incentives cannot be systematically avoided: any taxation mechanism that improves outcomes on one network must necessarily degrade them on another. Nonetheless, for the simple class of parallel networks, non-perverse taxes do exist; we fully characterize all such taxation mechanisms, showing that they are a generalized version of traditional marginal-cost tolls.

cs.GT↗

arXiv2019

Carrots or Sticks? The Effectiveness of Subsidies and Tolls in Congestion Games

Are rewards or penalties more effective in influencing user behavior? This work compares the effectiveness of subsidies and tolls in incentivizing users in congestion games. The predominantly studied method of influencing user behavior in network routing problems is to institute taxes which alter users' observed costs in a manner that causes their self-interested choices to more closely align with a system-level objective. Another feasible method to accomplish the same goal is to subsidize the users' actions that are preferable from a system-level perspective. We show that, when users behave similarly and predictably, subsidies offer comparable performance guarantees to tolls while requiring smaller monetary transactions with users; however, in the presence of unknown player heterogeneity, subsidies fail to offer the same performance as tolls. We further investigate these relationships in affine congestion games, deriving explicit performance bounds under optimal tolls and subsidies with and without user heterogeneity; we show that the differences in performance can be significant.

cs.GT↗

arXiv2019

Characterizing the interplay between information and strength in Blotto games

In this paper, we investigate informational asymmetries in the Colonel Blotto game, a game-theoretic model of competitive resource allocation between two players over a set of battlefields. The battlefield valuations are subject to randomness. One of the two players knows the valuations with certainty. The other knows only a distribution on the battlefield realizations. However, the informed player has fewer resources to allocate. We characterize unique equilibrium payoffs in a two battlefield setup of the Colonel Blotto game. We then focus on a three battlefield setup in the General Lotto game, a popular variant of the Colonel Blotto game. We characterize the unique equilibrium payoffs and mixed equilibrium strategies. We quantify the value of information - the difference in equilibrium payoff between the asymmetric information game and complete information game. We find information strictly improves the informed player's performance guarantee. However, the magnitude of improvement varies with the informed player's strength as well as the game parameters. Our analysis highlights the interplay between strength and information in adversarial environments.

cs.GT↗

arXiv2019

Utility Design for Distributed Resource Allocation -- Part I: Characterizing and Optimizing the Exact Price of Anarchy

Game theory has emerged as a fruitful paradigm for the design of networked multiagent systems. A fundamental component of this approach is the design of agents' utility functions so that their self-interested maximization results in a desirable collective behavior. In this work we focus on a well-studied class of distributed resource allocation problems where each agent is requested to select a subset of resources with the goal of optimizing a given system-level objective. Our core contribution is the development of a novel framework to tightly characterize the worst case performance of any resulting Nash equilibrium (price of anarchy) as a function of the chosen agents' utility functions. Leveraging this result, we identify how to design such utilities so as to optimize the price of anarchy through a tractable linear program. This provides us with a priori performance certificates applicable to any existing learning algorithm capable of driving the system to an equilibrium. Part II of this work specializes these results to submodular and supermodular objectives, discusses the complexity of computing Nash equilibria, and provides multiple illustrations of the theoretical findings.

cs.GT↗

arXiv2019

Utilizing Information Optimally to Influence Distributed Network Routing

How can a system designer exploit system-level knowledge to derive incentives to optimally influence social behavior? The literature on network routing contains many results studying the application of monetary tolls to influence behavior and improve the efficiency of self-interested network traffic routing. These results typically fall into two categories: (1) optimal tolls which incentivize socially-optimal behavior for a known realization of the network and population, or (2) robust tolls which provably reduce congestion given uncertainty regarding networks and user types, but may fail to optimize routing in general. This paper advances the study of robust influencing, mechanisms asking how a system designer can optimally exploit additional information regarding the network structure and user price sensitivities to design pricing mechanisms which influence behavior. We design optimal scaled marginal-cost pricing mechanisms for a class of parallel-network routing games and derive the tight performance guarantees when the network structure and/or the average user price-sensitivity is known. Our results demonstrate that from the standpoint of the system operator, in general it is more important to know the structure of the network than it is to know distributional information regarding the user population.

cs.GT↗

arXiv2019

A risk-security tradeoff in graphical coordination games

A system relying on the collective behavior of decision-makers can be vulnerable to a variety of adversarial attacks. How well can a system operator protect performance in the face of these risks? We frame this question in the context of graphical coordination games, where the agents in a network choose among two conventions and derive benefits from coordinating neighbors, and system performance is measured in terms of the agents' welfare. In this paper, we assess an operator's ability to mitigate two types of adversarial attacks - 1) broad attacks, where the adversary incentivizes all agents in the network and 2) focused attacks, where the adversary can force a selected subset of the agents to commit to a prescribed convention. As a mitigation strategy, the system operator can implement a class of distributed algorithms that govern the agents' decision-making process. Our main contribution characterizes the operator's fundamental trade-off between security against worst-case broad attacks and vulnerability from focused attacks. We show that this tradeoff significantly improves when the operator selects a decision-making process at random. Our work highlights the design challenges a system operator faces in maintaining resilience of networked distributed systems.

eess.SY↗

arXiv2019

Optimal Price of Anarchy in Cost-Sharing Games

The design of distributed algorithms is central to the study of multiagent systems control. In this paper, we consider a class of combinatorial cost-minimization problems and propose a framework for designing distributed algorithms with a priori performance guarantees that are near-optimal. We approach this problem from a game-theoretic perspective, assigning agents cost functions such that the equilibrium efficiency (price of anarchy) is optimized. Once agents' cost functions have been specified, any algorithm capable of computing a Nash equilibrium of the system inherits a performance guarantee matching the price of anarchy. Towards this goal, we formulate the problem of computing the price of anarchy as a tractable linear program. We then present a framework for designing agents' local cost functions in order to optimize for the worst-case equilibrium efficiency. Finally, we investigate the implications of our findings when this framework is applied to systems with convex, nondecreasing costs.

eess.SY↗

arXiv2019

The Impact of Information in Greedy Submodular Maximization

The maximization of submodular functions is an NP-Hard problem for certain subclasses of functions, for which a simple greedy algorithm has been shown to guarantee a solution whose quality is within 1/2 of the optimal. When this algorithm is implemented in a distributed way, agents sequentially make decisions based on the decisions of all previous agents. This work explores how limited access to the decisions of previous agents affects the quality of the solution of the greedy algorithm. Specifically, we provide tight upper and lower bounds on how well the algorithm performs, as a function of the information available to each agent. Intuitively, the results show that performance roughly degrades proportionally to the size of the largest group of agents which make decisions independently. Additionally, we consider the case where a system designer is given a set of agents and a global limit on the amount of information that can be accessed. Our results show that the best designs partition the agents into equally-sized sets and allow agents to access the decisions of all previous agents within the same set.

cs.DS↗

arXiv2018

The Importance of System-Level Information in Multiagent Systems Design: Cardinality and Covering Problems

A fundamental challenge in multiagent systems is to design local control algorithms to ensure a desirable collective behaviour. The information available to the agents, gathered either through communication or sensing, naturally restricts the achievable performance. Hence, it is fundamental to identify what piece of information is valuable and can be exploited to design control laws with enhanced performance guarantees. This paper studies the case when such information is uncertain or inaccessible for a class of submodular resource allocation problems termed covering problems. In the first part of this work we pinpoint a fundamental risk-reward tradeoff faced by the system operator when conditioning the control design on a valuable but uncertain piece of information, which we refer to as the cardinality, that represents the maximum number of agents that can simultaneously select any given resource. Building on this analysis, we propose a distributed algorithm that allows agents to learn the cardinality while adjusting their behaviour over time. This algorithm is proved to perform on par or better to the optimal design obtained when the exact cardinality is known a priori.

cs.GT↗

arXiv2017

Security Against Impersonation Attacks in Distributed Systems

In a multi-agent system, transitioning from a centralized to a distributed decision-making strategy can introduce vulnerability to adversarial manipulation. We study the potential for adversarial manipulation in a class of graphical coordination games where the adversary can pose as a friendly agent in the game, thereby influencing the decision-making rules of a subset of agents. The adversary's influence can cascade throughout the system, indirectly influencing other agents' behavior and significantly impacting the emergent collective behavior. The main results in this paper focus on characterizing conditions under which the adversary's local influence can dramatically impact the emergent global behavior, e.g., destabilize efficient Nash equilibria.

cs.GT↗

arXiv2017

Are Multiagent Systems Resilient to Communication Failures?

A challenge in multiagent control systems is to ensure that they are appropriately resilient to communication failures between the various agents. In many common game-theoretic formulations of these types of systems, it is implicitly assumed that all agents have access to as much information about other agents' actions as needed. This paper endeavors to augment these game-theoretic methods with policies that would allow agents to react on-the-fly to losses of this information. Unfortunately, we show that even if a single agent loses communication with one other weakly-coupled agent, this can cause arbitrarily-bad system states to emerge as various solution concepts of an associated game, regardless of how the agent accounts for the communication failure and regardless of how weakly coupled the agents are. Nonetheless, we show that the harm that communication failures can cause is limited by the structure of the problem; when agents' action spaces are richer, problems are more susceptible to these types of pathologies. Finally, we undertake an initial study into how a system designer might prevent these pathologies, and explore a few limited settings in which communication failures cannot cause harm.

cs.GT↗

arXiv2015

Learning Efficient Correlated Equilibria

The majority of distributed learning literature focuses on convergence to Nash equilibria. Correlated equilibria, on the other hand, can often characterize more efficient collective behavior than even the best Nash equilibrium. However, there are no existing distributed learning algorithms that converge to specific correlated equilibria. In this paper, we provide one such algorithm which guarantees that the agents' collective joint strategy will constitute an efficient correlated equilibrium with high probability. The key to attaining efficient correlated behavior through distributed learning involves incorporating a common random signal into the learning environment.

cs.GT↗

arXiv2014

Potential Games are Necessary to Ensure Pure Nash Equilibria in Cost Sharing Games

We consider the problem of designing distribution rules to share "welfare" (cost or revenue) among individually strategic agents. There are many known distribution rules that guarantee the existence of a (pure) Nash equilibrium in this setting, e.g., the Shapley value and its weighted variants; however, a characterization of the space of distribution rules that guarantee the existence of a Nash equilibrium is unknown. Our work provides an exact characterization of this space for a specific class of scalable and separable games, which includes a variety of applications such as facility location, routing, network formation, and coverage games. Given arbitrary local welfare functions W, we prove that a distribution rule guarantees equilibrium existence for all games (i.e., all possible sets of resources, agent action sets, etc.) if and only if it is equivalent to a generalized weighted Shapley value on some "ground" welfare functions W', which can be distinct from W. However, if budget-balance is required in addition to the existence of a Nash equilibrium, then W' must be the same as W. We also provide an alternate characterization of this space in terms of "generalized" marginal contributions, which is more appealing from the point of view of computational tractability. A possibly surprising consequence of our result is that, in order to guarantee equilibrium existence in all games with any fixed local welfare functions, it is necessary to work within the class of potential games.

cs.GT↗