Results 1 
7 of
7
Distributed Algorithmic Mechanism Design: Recent Results and Future Directions
, 2002
"... Distributed Algorithmic Mechanism Design (DAMD) combines theoretical computer science’s traditional focus on computational tractability with its more recent interest in incentive compatibility and distributed computing. The Internet’s decentralized nature, in which distributed computation and autono ..."
Abstract

Cited by 283 (24 self)
 Add to MetaCart
Distributed Algorithmic Mechanism Design (DAMD) combines theoretical computer science’s traditional focus on computational tractability with its more recent interest in incentive compatibility and distributed computing. The Internet’s decentralized nature, in which distributed computation and autonomous agents prevail, makes DAMD a very natural approach for many Internet problems. This paper first outlines the basics of DAMD and then reviews previous DAMD results on multicast cost sharing and interdomain routing. The remainder of the paper describes several promising research directions and poses some specific open problems.
Routing without regret: On convergence to nash equilibria of regretminimizing algorithms in routing games
 In PODC
, 2006
"... Abstract There has been substantial work developing simple, efficient noregret algorithms for a wideclass of repeated decisionmaking problems including online routing. These are adaptive strategies an individual can use that give strong guarantees on performance even in adversariallychanging envi ..."
Abstract

Cited by 58 (7 self)
 Add to MetaCart
(Show Context)
Abstract There has been substantial work developing simple, efficient noregret algorithms for a wideclass of repeated decisionmaking problems including online routing. These are adaptive strategies an individual can use that give strong guarantees on performance even in adversariallychanging environments. There has also been substantial work on analyzing properties of Nash equilibria in routing games. In this paper, we consider the question: if each player in a routing game uses a noregret strategy, will behavior converge to a Nash equilibrium? In general games the answer to this question is known to be no in a strong sense, but routing games havesubstantially more structure. In this paper we show that in the Wardrop setting of multicommodity flow and infinitesimalagents, behavior will approach Nash equilibrium (formally, on most days, the cost of the flow will be close to the cost of the cheapest paths possible given that flow) at a rate that dependspolynomially on the players ' regret bounds and the maximum slope of any latency function. We also show that priceofanarchy results may be applied to these approximate equilibria, and alsoconsider the finitesize (noninfinitesimal) loadbalancing model of Azar [2].
The Possible and the Impossible in MultiAgent Learning
, 2006
"... The paper surveys recent work on learning in games and delineates the boundary between forms of learning that lead to Nash equilibrium and forms that lead to weaker notions of equilibrium (or none at all). ..."
Abstract

Cited by 6 (0 self)
 Add to MetaCart
The paper surveys recent work on learning in games and delineates the boundary between forms of learning that lead to Nash equilibrium and forms that lead to weaker notions of equilibrium (or none at all).
Maximum Causal Entropy Correlated Equilibria for Markov Games
"... Motivated by a machine learning perspective—that gametheoretic equilibria constraints should serve as guidelines for predicting agents ’ strategies, we introduce maximum causal entropy correlated equilibria (MCECE), a novel solution concept for generalsum Markov games. In line with this perspective ..."
Abstract

Cited by 3 (2 self)
 Add to MetaCart
Motivated by a machine learning perspective—that gametheoretic equilibria constraints should serve as guidelines for predicting agents ’ strategies, we introduce maximum causal entropy correlated equilibria (MCECE), a novel solution concept for generalsum Markov games. In line with this perspective, a MCECE strategy profile is a uniquelydefined joint probability distribution over actions for each game state that minimizes the worstcase prediction of agents ’ actions under logloss. Equivalently, it maximizes the worstcase growth rate for gambling on the sequences of agents’ joint actions under uniform odds. We present a convex optimization technique for obtaining MCECE strategy profiles that resembles value iteration in finitehorizon games. We assess the predictive benefits of our approach by predicting the strategies generated by previously proposed correlated equilibria solution concepts, and compare against those previous approaches on that same prediction task.
for Markov Games
"... Motivated by a machine learning perspective—that gametheoretic equilibria constraints should serve as guidelines for predicting agents ’ strategies, we introduce maximum causal entropy correlated equilibria (MCECE), a novel solution concept for generalsum Markov games. In line with this perspective ..."
Abstract
 Add to MetaCart
Motivated by a machine learning perspective—that gametheoretic equilibria constraints should serve as guidelines for predicting agents ’ strategies, we introduce maximum causal entropy correlated equilibria (MCECE), a novel solution concept for generalsum Markov games. In line with this perspective, a MCECE strategy profile is a uniquelydefined joint probability distribution over actions for each game state that minimizes the worstcase prediction of agents ’ actions under logloss. Equivalently, it maximizes the worstcase growth rate for gambling on the sequences of agents’ joint actions under uniform odds. We present a convex optimization technique for obtaining MCECE strategy profiles that resembles value iteration in finitehorizon games. We assess the predictive benefits of our approach by predicting the strategies generated by previously proposed correlated equilibria solution concepts, and compare against those previous approaches on that same prediction task.
CMUML08112 On Fixed Convex Combinations of NoRegret Learners
, 2008
"... Noregret algorithms are powerful tools for learning in online convex problems that have received increased attention in recent years. Considering affine and external regret, we investigate what happens when a set of noregret learners (voters) merge their respective strategies in each learning iter ..."
Abstract
 Add to MetaCart
(Show Context)
Noregret algorithms are powerful tools for learning in online convex problems that have received increased attention in recent years. Considering affine and external regret, we investigate what happens when a set of noregret learners (voters) merge their respective strategies in each learning iteration to a single, common one in form of a convex combination. We show that an agent who executes this merged decision in each iteration of the online learning process and each time feeds back a reward function to the voters that is a correspondingly weighted version of its own reward, incurs sublinear regret itself. As a byproduct, we obtain a simple method that allows us