Skip to yearly menu bar Skip to main content


Per-Decision Option Discounting

Anna Harutyunyan · Peter Vrancx · Philippe Hamel · Ann Nowe · Doina Precup

Pacific Ballroom #114

Keywords: [ Theory and Algorithms ] [ Planning and Control ]


In order to solve complex problems an agent must be able to reason over a sufficiently long horizon. Temporal abstraction, commonly modeled through options, offers the ability to reason at many timescales, but the horizon length is still determined by the discount factor of the underlying Markov Decision Process. We propose a modification to the options framework that naturally scales the agent's horizon with option length. We show that the proposed option-step discount controls a bias-variance trade-off, with larger discounts (counter-intuitively) leading to less estimation variance.

Live content is unavailable. Log in and register to view live content