Inferential Induction: A Novel Framework for Bayesian Reinforcement Learning - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2020

Inferential Induction: A Novel Framework for Bayesian Reinforcement Learning

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.
Fichier principal
Vignette du fichier
inferential_induction_a_novel_framework_for_bayesian_reinforcement_learning.pdf (4.06 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03125100 , version 1 (29-01-2021)

Identifiers

  • HAL Id : hal-03125100 , version 1

Cite

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⟩
74 View
32 Download

Share

Gmail Facebook Twitter LinkedIn More