A Normative Account of Confirmation Bias During Reinforcement Learning

DOI10.1162/NECO_A_01455MaRDI QIDQ5037149zbMATH OpenOpenAlexWikidataFDO

Authors Germain Lefebvre, Christopher Summerfield, Rafal Bogacz

Publication date 25 February 2022

Published in Neural Computation (Search for Journal in Brave)

Copyright license Creative Commons Attribution-NonCommercial 4.0 International

Full work available at URL https://doi.org/10.1162/neco_a_01455

Mathematics Subject Classification ID

Computer science (68-XX)

Recommendations

• Confidence biases and learning among intuitive Bayesians
• Learning and self-confirming long-run biases
• Evidence for learning to learn behavior in normal form games
• Testing models of belief bias: an experiment
• Learning Declarative Bias

Cites work

• Bounded Ornstein-Uhlenbeck models for two-choice time controlled tasks
• The statistical structures of reinforcement learning with asymmetric value updates

This page was built for publication: A Normative Account of Confirmation Bias During Reinforcement Learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5037149)