Leadership in Congestion Games: Multiple User Classes and Non-Singleton Actions (Extended Version)

We study the problem of finding Stackelberg equilibria in games with a massive number of players. So far, the only known game instances in which the problem is solved in polynomial time are some particular congestion games. However, a complete characterization of hard and easy instances is still lacking. In this paper, we extend the state of the art along two main directions. First, we focus on games where players' actions are made of multiple resources, and we prove that the problem is NP-hard and not in Poly-APX unless P = NP, even in the basic case in which players are symmetric, their actions are made of only two resources, and the cost functions are monotonic. Second, we focus on games with singleton actions where the players are partitioned into classes, depending on which actions they have available. In this case, we provide a dynamic programming algorithm that finds an equilibrium in polynomial time, when the number of classes is fixed and the leader plays pure strategies. Moreover, we prove that, if we allow for leader's mixed strategies, then the problem becomes NP-hard even with only four classes and monotonic costs. Finally, for both settings, we provide mixed-integer linear programming formulations, and we experimentally evaluate their scalability on both random game instances and worst-case instances based on our hardness reductions.

[1]  Stefano Coniglio,et al.  Leadership in Singleton Congestion Games , 2018, IJCAI.

[2]  Stefano Coniglio,et al.  Pessimistic Leader-Follower Equilibria with Multiple Followers , 2017, IJCAI.

[3]  Stefano Coniglio,et al.  Bilevel programming methods for computing single-leader-multi-follower equilibria in normal-form and polymatrix games , 2020, EURO J. Comput. Optim..

[4]  Berthold Vöcking,et al.  On the Impact of Combinatorial Structure on Congestion Games , 2006, FOCS.

[5]  J. Nash NON-COOPERATIVE GAMES , 1951, Classics in Game Theory.

[6]  Stefano Coniglio,et al.  Methods for Finding Leader-Follower Equilibria with Multiple Followers: (Extended Abstract) , 2016, AAMAS.

[7]  Marc Uetz,et al.  The Sequential Price of Anarchy for Atomic Congestion Games , 2014, WINE.

[8]  Vincent Conitzer,et al.  Commitment to Correlated Strategies , 2011, AAAI.

[9]  Yoav Shoham,et al.  Fast and Compact: A Simple Class of Congestion Games , 2005, AAAI.

[10]  Nicola Gatti,et al.  Be a Leader or Become a Follower: The Strategy to Commit to with Multiple Leaders (Extended Version) , 2019, IJCAI.

[11]  Christos H. Papadimitriou,et al.  The complexity of pure Nash equilibria , 2004, STOC '04.

[12]  Bernhard von Stengel,et al.  Leadership games with convex strategy sets , 2010, Games Econ. Behav..

[13]  Sarit Kraus,et al.  Playing games for security: an efficient exact algorithm for solving Bayesian Stackelberg games , 2008, AAMAS.

[14]  Dimitris Fotakis,et al.  Stackelberg Strategies for Atomic Congestion Games , 2007, Theory of Computing Systems.

[15]  José R. Correa,et al.  The Curse of Sequentiality in Routing Games , 2015, WINE.

[16]  Renato F. Werneck,et al.  Finding minimum congestion spanning trees , 1999, JEAL.

[17]  L. Shapley,et al.  Potential Games , 1994 .

[18]  Chaitanya Swamy,et al.  The effectiveness of Stackelberg strategies and tolls for network congestion games , 2007, SODA '07.

[19]  Tim Roughgarden Stackelberg Scheduling Strategies , 2004, SIAM J. Comput..

[20]  Garth P. McCormick,et al.  Computability of global solutions to factorable nonconvex programs: Part I — Convex underestimating problems , 1976, Math. Program..

[21]  Milind Tambe,et al.  Security and Game Theory - Algorithms, Deployed Systems, Lessons Learned , 2011 .

[22]  Milind Tambe Security and Game Theory: EFFICIENT ALGORITHMS FOR MASSIVE SECURITY GAMES , 2011 .

[23]  Stefano Coniglio,et al.  Leadership in Singleton Congestion Games: What is Hard and What is Easy , 2018, Artif. Intell..

[24]  Peter C. Cheeseman,et al.  Where the Really Hard Problems Are , 1991, IJCAI.

[25]  David P. Williamson,et al.  Stackelberg thresholds in network routing games or the value of altruism , 2007, EC '07.

[26]  R. Rosenthal A class of games possessing pure-strategy Nash equilibria , 1973 .

[27]  Vincent Conitzer,et al.  Mixed-Integer Programming Methods for Finding Nash Equilibria , 2005, AAAI.

[28]  R. Aumann Subjectivity and Correlation in Randomized Strategies , 1974 .

[29]  David S. Johnson,et al.  Computers and Intractability: A Guide to the Theory of NP-Completeness , 1978 .

[30]  Stefano Coniglio,et al.  Computing a Pessimistic Leader-Follower Equilibrium with Multiple Followers: the Mixed-Pure Case , 2018, ArXiv.

[31]  Vincent Conitzer,et al.  Computing the optimal strategy to commit to , 2006, EC '06.

[32]  Renato Paes Leme,et al.  The curse of simultaneity , 2012, ITCS '12.

[33]  Stefano Coniglio,et al.  Bilevel Programming Approaches to the Computation of Optimistic and Pessimistic Single-Leader-Multi-Follower Equilibria , 2017, SEA.