HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

Inferential Induction: A Novel Framework for Bayesian Reinforcement Learning

Emilio Jorge 1 Hannes Eriksson 1 Christos Dimitrakakis 1, 2 Debabrota Basu 3, 1 Divya Grover 1
3 Scool - Scool
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
Abstract : Bayesian Reinforcement Learning (BRL) offers a decision-theoretic solution to the reinforcement learning problem. While “model-based” BRL algorithms have focused either on maintaining a posterior distribution on models, BRL “model-free” methods try to estimate value function distributions but make strong implicit assumptions or approximations. We describe a novel Bayesian framework, inferential induction, for correctly inferring value function distributions from data, which leads to a new family of BRL algorithms. We design an algorithm, Bayesian Backwards Induction (BBI), with this framework. We experimentally demonstrate that BBI is competitive with the state of the art. However, its advantage relative to existing BRL model-free methods is not as great as we have expected, particularly when the additional computational burden is taken into account.
Complete list of metadata

Contributor : Debabrota Basu Connect in order to contact the contributor
Submitted on : Friday, January 29, 2021 - 11:20:33 AM
Last modification on : Thursday, March 24, 2022 - 3:42:47 AM
Long-term archiving on: : Friday, April 30, 2021 - 6:42:22 PM


Files produced by the author(s)


  • HAL Id : hal-03125100, version 1


Emilio Jorge, Hannes Eriksson, Christos Dimitrakakis, Debabrota Basu, Divya Grover. Inferential Induction: A Novel Framework for Bayesian Reinforcement Learning. "I Can't Believe It's Not Better!" at NeurIPS Workshops, Dec 2020, Vancouver, Canada. pp.43-52. ⟨hal-03125100⟩



Record views


Files downloads