Papers
Topics
Authors
Recent
Search
2000 character limit reached

Polynomial-Time Computation of Exact $Φ$-Equilibria in Polyhedral Games

Published 26 Feb 2024 in cs.GT | (2402.16316v2)

Abstract: It is a well-known fact that correlated equilibria can be computed in polynomial time in a large class of concisely represented games using the celebrated Ellipsoid Against Hope algorithm (Papadimitriou and Roughgarden, 2008; Jiang and Leyton-Brown, 2015). However, the landscape of efficiently computable equilibria in sequential (extensive-form) games remains unknown. The Ellipsoid Against Hope does not apply directly to these games, because they do not have the required "polynomial type" property. Despite this barrier, Huang and von Stengel (2008) altered the algorithm to compute exact extensive-form correlated equilibria. In this paper, we generalize the Ellipsoid Against Hope and develop a simple algorithmic framework for efficiently computing saddle-points in bilinear zero-sum games, even when one of the dimensions is exponentially large. Moreover, the framework only requires a "good-enough-response" oracle, which is a weakened notion of a best-response oracle. Using this machinery, we develop a general algorithmic framework for computing exact linear $\Phi$-equilibria in any polyhedral game (under mild assumptions), including correlated equilibria in normal-form games, and extensive-form correlated equilibria in extensive-form games. This enables us to give the first polynomial-time algorithm for computing exact linear-deviation correlated equilibria in extensive-form games, thus resolving an open question by Farina and Pipis (2023). Furthermore, even for the cases for which a polynomial time algorithm for exact equilibria was already known, our framework provides a conceptually simpler solution.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. From Duels to Battlefields: Computing Equilibria of Blotto and Other Games. Mathematics of Operations Research 44, 4 (2019), 1304–1325.
  2. Near-Optimal No-Regret Learning for Correlated Equilibria in Multi-Player General-Sum Games. In ACM Symposium on Theory of Computing.
  3. Online Learning and Solving Infinite Games with an ERM Oracle. In The Thirty Sixth Annual Conference on Learning Theory, COLT 2023, 12-15 July 2023, Bangalore, India (Proceedings of Machine Learning Research, Vol. 195), Gergely Neu and Lorenzo Rosasco (Eds.). PMLR, 274–324.
  4. Robert J Aumann. 1974. Subjectivity and correlation in randomized strategies. Journal of mathematical Economics 1, 1 (1974), 67–96.
  5. Avrim Blum and Yishay Mansour. 2007. From External to Internal Regret. J. Mach. Learn. Res. 8 (2007).
  6. G.W. Brown. 1951. Iterative Solutions of Games by Fictitious Play. In Activity Analysis of Production and Allocation, T. C. Koopmans (Ed.). Wiley, New York.
  7. Efficient Learning in Polyhedral Games via Best Response Oracles. In AAAI Conference on Artificial Intelligence (AAAI).
  8. From External to Swap Regret 2.0: An Efficient Reduction and Oblivious Adversary for Large Action Spaces. arXiv:2310.19786 [cs.LG]
  9. The complexity of computing a Nash equilibrium. Commun. ACM 52, 2 (feb 2009), 89–97.
  10. Human-level play in the game of Diplomacy by combining language models with strategic reasoning. Science 378, 6624 (2022), 1067–1074.
  11. Coarse Correlation in Extensive-Form Games. In AAAI Conference on Artificial Intelligence.
  12. Simple Uncoupled No-regret Learning Dynamics for Extensive-form Correlated Equilibrium. J. ACM 69, 6 (2022).
  13. Kernelized Multiplicative Weights for 0/1-Polyhedral Games: Bridging the Gap Between Learning in Extensive-Form and Normal-Form Games. In International Conference on Machine Learning.
  14. Gabriele Farina and Charilaos Pipis. 2023. Polynomial-Time Linear-Swap Regret Minimization in Imperfect-Information Sequential Games. In Thirty-seventh Conference on Neural Information Processing Systems.
  15. States as Strings as Strategies: Steering Language Models with Game-Theoretic Solvers. arXiv:2402.01704 [cs.CL]
  16. Frank-Wolfe Algorithms for Saddle Point Problems. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research, Vol. 54), Aarti Singh and Jerry Zhu (Eds.). PMLR, 362–371.
  17. Paul W. Goldberg and Francisco J. Marmolejo-Cossío. 2021. Learning Convex Partitions and Computing Game-theoretic Equilibria from Best-response Queries. ACM Transactions on Economics and Computation 9, 1 (2021), 3:1–3:36.
  18. No-regret learning in convex games. In International Conference on Machine learning. 360–367.
  19. Geometric Algorithms and Combinatorial Optimization. Springer Berlin, Heidelberg.
  20. Sergiu Hart and Andreu Mas-Colell. 2000. A Simple Adaptive Procedure Leading to Correlated Equilibrium. Econometrica 68, 5 (2000), 1127–1150.
  21. Sergiu Hart and David Schmeidler. 1989. Existence of Correlated Equilibria. Mathematics of Operations Research 14, 1 (1989), 18–25.
  22. Elad Hazan and Satyen Kale. 2007. Computational Equivalence of Fixed Points and No Regret Algorithms, and Convergence to Equilibria. In Advances in Neural Information Processing Systems, J. Platt, D. Koller, Y. Singer, and S. Roweis (Eds.), Vol. 20. Curran Associates, Inc.
  23. Wan Huang and Bernhard von Stengel. 2008. Computing an extensive-form correlated equilibrium in polynomial time. In International Workshop on Internet and Network Economics. Springer, 506–513.
  24. Albert Xin Jiang and Kevin Leyton-Brown. 2015. Polynomial-time computation of exact correlated equilibrium in compact games. Games and Economic Behavior 91 (2015), 347–359.
  25. Computing optimal randomized resource allocations for massive security games. In Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems - Volume 1 (Budapest, Hungary) (AAMAS ’09). International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC, 689–696.
  26. Efficient Computation of Equilibria for Extensive Two-Person Games. Games and Economic Behavior 14, 2 (1996), 247–259.
  27. Hedging Structured Concepts. In COLT. Citeseer, 93–105.
  28. A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 4190–4203.
  29. C. Marks. 2008. No-regret learning and game-theoretic equilibria. Ph. D. Dissertation. Brown University, Providence, RI.
  30. Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139). PMLR, 7818–7828.
  31. H. Moulin and J. P. Vial. 1978. Strategically zero-sum games: The class of games whose completely mixed equilibria cannot be improved upon. Int. J. Game Theory 7, 3–4 (sep 1978), 201–221.
  32. J. von Neumann. 1928. Zur Theorie der Gesellschaftsspiele. Math. Ann. 100, 1 (1928), 295–320.
  33. Christos H. Papadimitriou and Tim Roughgarden. 2008. Computing Correlated Equilibria in Multi-Player Games. J. ACM 55, 3 (2008).
  34. Binghui Peng and Aviad Rubinstein. 2023. Fast swap regret minimization and applications to approximate correlated equilibria. arXiv:2310.19647 [cs.GT]
  35. I. Romanovskii. 1962. Reduction of a Game with Complete Memory to a Matrix Game. Soviet Mathematics 3 (1962).
  36. Aviad Rubinstein. 2015. Inapproximability of Nash Equilibrium. In Proceedings of the Forty-Seventh Annual ACM Symposium on Theory of Computing (Portland, Oregon, USA) (STOC ’15). Association for Computing Machinery, New York, NY, USA, 409–418.
  37. Aviad Rubinstein. 2016. Settling the Complexity of Computing Approximate Two-Player Nash Equilibria. In 2016 IEEE 57th Annual Symposium on Foundations of Computer Science (FOCS). 258–265.
  38. Eiji Takimoto and Manfred K Warmuth. 2003. Path kernels and multiplicative updates. The Journal of Machine Learning Research 4 (2003), 773–818.
  39. Bernhard von Stengel. 1996. Efficient Computation of Behavior Strategies. Games and Economic Behavior 14, 2 (1996), 220–246.
  40. B. von Stengel and F. Forges. 2008. Extensive-form correlated equilibrium: Definition and computational complexity. Mathematics of Operations Research 33, 4 (2008), 1002–1022.
  41. Haifeng Xu. 2016. The Mysteries of Security Games: Equilibrium Computation Becomes Combinatorial Algorithm Design. In Proceedings of the 2016 ACM Conference on Economics and Computation (Maastricht, The Netherlands) (EC ’16). Association for Computing Machinery, New York, NY, USA, 497–514.
  42. Solving Zero-Sum Security Games in Discretized Spatio-Temporal Domains. Proceedings of the AAAI Conference on Artificial Intelligence 28, 1 (Jun. 2014).
  43. Efficient ΦΦ\Phiroman_Φ-Regret Minimization with Low-Degree Swap Deviations in Extensive-Form Games. arXiv:2402.09670 [cs.GT]
  44. Mediator Interpretation and Faster Learning Algorithms for Linear Correlated Equilibria in General Sequential Games. In The Twelfth International Conference on Learning Representations.
Citations (3)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up

Tweets

Sign up for free to view the 2 tweets with 1 like about this paper.

Sign Up for Free