Publications

| Sorted by Date | Classified by Publication Type | Classified by Research Category |

Bayesian Deep Q-Learning via Sequential Monte Carlo

Pascal Van der Vaart, Matthijs T. J. Spaan, and Neil Yorke-Smith. Bayesian Deep Q-Learning via Sequential Monte Carlo. In European Workshop on Reinforcement Learning, 2023.

Download

pdf 

Abstract

Exploration in reinforcement learning remains a difficult challenge. Recently, ensembles with randomized prior functions have been popularized to quantify uncertainty in the value model, in order to drive exploration with success. However these ensembles have no theoretical guarantee to resemble the actual posterior. In this work, we view training ensembles from the perspective of sequential Monte Carlo, and propose an algorithm that exploits both the practical flexibility of ensembles and theory of the Bayesian paradigm. We incorporate this method into a standard DQN agent and experimentally show improved exploration capabilities over a regular ensemble.

BibTeX Entry

@InProceedings{VanDerVaart23ewrl,
  author =       {Van der Vaart, Pascal and Spaan, Matthijs T. J. and
                  Yorke-Smith, Neil},
  title =        {Bayesian Deep {Q}-Learning via Sequential {M}onte {C}arlo},
  year =         2023,
  booktitle =    {European Workshop on Reinforcement Learning},
}

Note: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Generated by bib2html.pl (written by Patrick Riley) on Thu Feb 29, 2024 16:15:45 UTC