Best-Response Bayesian Reinforcement Learning with Bayes-adaptive POMDPs for Centaurs

Mustafa Mert Celikok, Frans A. Oliehoek, Samuel Kaski

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Centaurs are half-human, half-AI decision-makers where the AI's goal is to complement the human. To do so, the AI must be able to recognize the goals and constraints of the human and have the means to help them. We present a novel formulation of the interaction between the human and the AI as a sequential game where the agents are modelled using Bayesian best-response models. We show that in this case the AI's problem of helping bounded-rational humans make better decisions reduces to a Bayes-adaptive POMDP. In our simulated experiments, we consider an instantiation of our framework for humans who are subjectively optimistic about the AI's future behaviour. Our results show that when equipped with a model of the human, the AI can infer the human's bounds and nudge them towards better decisions. We discuss ways in which the machine can learn to improve upon its own limitations as well with the help of the human. We identify a novel trade-off for centaurs in partially observable tasks: for the AI's actions to be acceptable to the human, the machine must make sure their beliefs are sufficiently aligned, but aligning beliefs might be costly. We present a preliminary theoretical analysis of this trade-off and its dependence on task structure.

Original languageEnglish
Title of host publicationInternational Conference on Autonomous Agents and Multiagent Systems, AAMAS 2022
PublisherInternational Foundation for Autonomous Agents and Multiagent Systems
Number of pages9
ISBN (Electronic)9781713854333
Publication statusAccepted/In press - 3 Apr 2022
EventInternational Conference on Autonomous Agents and Multiagent Systems - Virtual, Online
Duration: 9 May 202213 May 2022


ConferenceInternational Conference on Autonomous Agents and Multiagent Systems


  • Bayesian Reinforcement Learning
  • Computational Rationality
  • Hybrid Intelligence
  • Multiagent Learning

Research Beacons, Institutes and Platforms

  • Institute for Data Science and AI
  • Digital Futures
  • Sustainable Futures


Dive into the research topics of 'Best-Response Bayesian Reinforcement Learning with Bayes-adaptive POMDPs for Centaurs'. Together they form a unique fingerprint.

Cite this