|COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring.|
Bayesian Reinforcement Learning
If you have a question about this talk, please contact Colorado Reed.
Reinforcement learning (RL) is the problem of learning optimal behaviour in an initially unfamiliar Markov Decision Process (MDP) environment through interaction and evaluative feedback. Until recently, existing RL algorithms have relied on non-optimal exploration strategies to strike a balance between ‘exploiting’ current knowledge of the MDP to maximise expected returns, and ‘exploration’ actions which gain information on the MDP , to improve the return on exploitation actions in the future. Bayesian Reinforcement learning (BRL) is about capturing and dealing with uncertainty in MDP elements, where ‘classic RL’ does not. We focus on modelling uncertainty in an agent’s transition probabilities, often termed ‘model-based’ BRL . By planning in a belief space of transition probabilities, BRL implicitly resolves the classic RL ‘exploitation & exploration’ dilemma optimally. Computation is shown to be intractable in general, although approximations exist of which several key algorithms are presented.
This talk is part of the Machine Learning Reading Group @ CUED series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
Other listsBMCS Postgraduate Symposium for Biological and Medicinal Chemists Sustainable Development: 11th Distinguished Lecture Series 2013 Gastrointestinal Cancer Forum
Other talksVan Dyck and Reynolds: Two giants of portraiture "Addressing missingness using two-phase sampling for nonresponse: methods and benefits" Capacity and Comprehension of Mathematical Reasoning by Counsel and Courts Forensic databases: size, completeness, usefulness The particulars of particulates Celebrating the 40th Anniversary of Mildred Taylor's Roll of Thunder, Hear My Cry