Corrupted Multidimensional Binary Search: Learning in the Presence of Irrational Agents

02/26/2020
by   Akshay Krishnamurthy, et al.
13

Standard game-theoretic formulations for settings like contextual pricing and security games assume that agents act in accordance with a specific behavioral model. In practice however, some agents may not prescribe to the dominant behavioral model or may act in ways that are arbitrarily inconsistent. Existing algorithms heavily depend on the model being (approximately) accurate for all agents and have poor performance in the presence of even a few such arbitrarily irrational agents. How do we design learning algorithms that are robust to the presence of arbitrarily irrational agents? We address this question for a number of canonical game-theoretic applications by designing a robust algorithm for the fundamental problem of multidimensional binary search. The performance of our algorithm degrades gracefully with the number of corrupted rounds, which correspond to irrational agents and need not be known in advance. As binary search is the key primitive in algorithms for contextual pricing, Stackelberg Security Games, and other game-theoretic applications, we immediately obtain robust algorithms for these settings. Our techniques draw inspiration from learning theory, game theory, high-dimensional geometry, and convex analysis, and may be of independent algorithmic interest.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/13/2023

Improving Quantal Cognitive Hierarchy Model Through Iterative Population Learning

In domains where agents interact strategically, game theory is applied w...
research
08/19/2022

Learning in Stackelberg Games with Non-myopic Agents

We study Stackelberg games where a principal repeatedly interacts with a...
research
12/15/2020

Evolutionary Game Theory Squared: Evolving Agents in Endogenously Evolving Zero-Sum Games

The predominant paradigm in evolutionary game theory and more generally ...
research
07/23/2018

Towards a Programmable Framework for Agent Game Playing

The field of Game Theory provides a useful mechanism for modeling many d...
research
06/08/2021

Balancing Asymptotic and Transient Efficiency Guarantees in Set Covering Games

Game theoretic approaches have gained traction as a robust methodology f...
research
07/26/2023

Corruption-Robust Lipschitz Contextual Search

I study the problem of learning a Lipschitz function with corrupted bina...

Please sign up or login with your details

Forgot password? Click here to reset