Abstract
Model-based reinforcement learning methods are promising since they can increase sample efficiency while simultaneously improving generalizability. Learning can also be made more efficient through state abstraction, which delivers more compact models. Model-based reinforcement learning methods have been combined with learning abstract models to profit from both effects. We consider a wide range of state abstractions that have been covered in the literature, from straightforward state aggregation to deep learned representations, and sketch challenges that arise when combining model-based reinforcement learning with abstraction. We further show how various methods deal with these challenges and point to open questions and opportunities for further research.
Original language | English |
---|---|
Title of host publication | 34th Benelux Conference on Artificial Intelligence (BNAIC) and the 30th Belgian Dutch Conference on Machine Learning (Benelearn) |
Editors | Toon Calders, Bart Goethals, Celine Vens, Jefrey Lijffijt |
Chapter | 16 |
Pages | 133–148 |
Number of pages | 16 |
DOIs | |
Publication status | Published - 2022 |
Event | 34th Benelux Conference on Artificial Intelligence (BNAIC) and the 30th Belgian Dutch Conference on Machine Learning (Benelearn) - Mechelen, Belgium Duration: 7 Nov 2022 → 9 Nov 2022 |
Publication series
Name | Communications in Computer and Information Science |
---|---|
Volume | 1805 CCIS |
ISSN (Print) | 1865-0929 |
ISSN (Electronic) | 1865-0937 |
Conference
Conference | 34th Benelux Conference on Artificial Intelligence (BNAIC) and the 30th Belgian Dutch Conference on Machine Learning (Benelearn) |
---|---|
Abbreviated title | BNAIC/BeNeLearn 2022 |
Country/Territory | Belgium |
City | Mechelen |
Period | 7/11/22 → 9/11/22 |
Bibliographical note
Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-careOtherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.
Keywords
- Model-Based RL
- State Abstraction
- MDPs