Separating value functions across time-scales

Joshua Romoff, Peter Henderson, Ahmed Touati, Emma Brunskill, Joelle Pineau, Yann Ollivier

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Scopus citations

Abstract

In many finite horizon episodic reinforcement learning (RL) settings, it is desirable to optimize for the undiscounted return - in settings like Atari, for instance, the goal is to collect the most points while staying alive in the long run. Yet, it may be difficult (or even intractable) mathematically to learn with this target. As such, temporal discounting is often applied to optimize over a shorter effective planning horizon. This comes at the risk of potentially biasing the optimization target away from the undiscounted goal. In settings where this bias is unacceptable - where the system must optimize for longer horizons at higher discounts - the target of the value function approximator may increase in variance leading to difficulties in learning. We present an extension of temporal difference (TD) learning, which we call TD(Δ), that breaks down a value function into a series of components based on the differences between value functions with smaller discount factors. The separation of a longer horizon value function into these components has useful properties in scalability and performance. We discuss these properties and show theoretic and empirical improvements over standard TD learning in certain settings.

Original languageEnglish (US)
Title of host publication36th International Conference on Machine Learning, ICML 2019
PublisherInternational Machine Learning Society (IMLS)
Pages9589-9642
Number of pages54
ISBN (Electronic)9781510886988
StatePublished - 2019
Externally publishedYes
Event36th International Conference on Machine Learning, ICML 2019 - Long Beach, United States
Duration: Jun 9 2019Jun 15 2019

Publication series

Name36th International Conference on Machine Learning, ICML 2019
Volume2019-June

Conference

Conference36th International Conference on Machine Learning, ICML 2019
Country/TerritoryUnited States
CityLong Beach
Period6/9/196/15/19

All Science Journal Classification (ASJC) codes

  • Education
  • Computer Science Applications
  • Human-Computer Interaction

Fingerprint

Dive into the research topics of 'Separating value functions across time-scales'. Together they form a unique fingerprint.

Cite this