Conditional swap regret and conditional correlated equilibrium

Mehryar Mohri, Scott Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We introduce a natural extension of the notion of swap regret, conditional swap regret, that allows for action modifications conditioned on the player's action history. We prove a series of new results for conditional swap regret minimization. We present algorithms for minimizing conditional swap regret with bounded conditioning history. We further extend these results to the case where conditional swaps are considered only for a subset of actions. We also define a new notion of equilibrium, conditional correlated equilibrium, that is tightly connected to the notion of conditional swap regret: when all players follow conditional swap regret minimization strategies, then the empirical distribution approaches this equilibrium. Finally, we extend our results to the multi-armed bandit scenario.

Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems
PublisherNeural information processing systems foundation
Pages1314-1322
Number of pages9
Volume2
EditionJanuary
StatePublished - 2014
Event28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014 - Montreal, Canada
Duration: Dec 8 2014Dec 13 2014

Other

Other28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014
CountryCanada
CityMontreal
Period12/8/1412/13/14

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Mohri, M., & Yang, S. (2014). Conditional swap regret and conditional correlated equilibrium. In Advances in Neural Information Processing Systems (January ed., Vol. 2, pp. 1314-1322). Neural information processing systems foundation.

Conditional swap regret and conditional correlated equilibrium. / Mohri, Mehryar; Yang, Scott.

Advances in Neural Information Processing Systems. Vol. 2 January. ed. Neural information processing systems foundation, 2014. p. 1314-1322.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mohri, M & Yang, S 2014, Conditional swap regret and conditional correlated equilibrium. in Advances in Neural Information Processing Systems. January edn, vol. 2, Neural information processing systems foundation, pp. 1314-1322, 28th Annual Conference on Neural Information Processing Systems 2014, NIPS 2014, Montreal, Canada, 12/8/14.
Mohri M, Yang S. Conditional swap regret and conditional correlated equilibrium. In Advances in Neural Information Processing Systems. January ed. Vol. 2. Neural information processing systems foundation. 2014. p. 1314-1322
Mohri, Mehryar ; Yang, Scott. / Conditional swap regret and conditional correlated equilibrium. Advances in Neural Information Processing Systems. Vol. 2 January. ed. Neural information processing systems foundation, 2014. pp. 1314-1322
@inproceedings{ad7ce5823579419e8f22d68cb99c9adb,
title = "Conditional swap regret and conditional correlated equilibrium",
abstract = "We introduce a natural extension of the notion of swap regret, conditional swap regret, that allows for action modifications conditioned on the player's action history. We prove a series of new results for conditional swap regret minimization. We present algorithms for minimizing conditional swap regret with bounded conditioning history. We further extend these results to the case where conditional swaps are considered only for a subset of actions. We also define a new notion of equilibrium, conditional correlated equilibrium, that is tightly connected to the notion of conditional swap regret: when all players follow conditional swap regret minimization strategies, then the empirical distribution approaches this equilibrium. Finally, we extend our results to the multi-armed bandit scenario.",
author = "Mehryar Mohri and Scott Yang",
year = "2014",
language = "English (US)",
volume = "2",
pages = "1314--1322",
booktitle = "Advances in Neural Information Processing Systems",
publisher = "Neural information processing systems foundation",
edition = "January",

}

TY - GEN

T1 - Conditional swap regret and conditional correlated equilibrium

AU - Mohri, Mehryar

AU - Yang, Scott

PY - 2014

Y1 - 2014

N2 - We introduce a natural extension of the notion of swap regret, conditional swap regret, that allows for action modifications conditioned on the player's action history. We prove a series of new results for conditional swap regret minimization. We present algorithms for minimizing conditional swap regret with bounded conditioning history. We further extend these results to the case where conditional swaps are considered only for a subset of actions. We also define a new notion of equilibrium, conditional correlated equilibrium, that is tightly connected to the notion of conditional swap regret: when all players follow conditional swap regret minimization strategies, then the empirical distribution approaches this equilibrium. Finally, we extend our results to the multi-armed bandit scenario.

AB - We introduce a natural extension of the notion of swap regret, conditional swap regret, that allows for action modifications conditioned on the player's action history. We prove a series of new results for conditional swap regret minimization. We present algorithms for minimizing conditional swap regret with bounded conditioning history. We further extend these results to the case where conditional swaps are considered only for a subset of actions. We also define a new notion of equilibrium, conditional correlated equilibrium, that is tightly connected to the notion of conditional swap regret: when all players follow conditional swap regret minimization strategies, then the empirical distribution approaches this equilibrium. Finally, we extend our results to the multi-armed bandit scenario.

UR - http://www.scopus.com/inward/record.url?scp=84937916646&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84937916646&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2

SP - 1314

EP - 1322

BT - Advances in Neural Information Processing Systems

PB - Neural information processing systems foundation

ER -