English

Posterior Sampling for Large Scale Reinforcement Learning

Machine Learning 2018-10-24 v3 Artificial Intelligence

Abstract

We propose a practical non-episodic PSRL algorithm that unlike recent state-of-the-art PSRL algorithms uses a deterministic, model-independent episode switching schedule. Our algorithm termed deterministic schedule PSRL (DS-PSRL) is efficient in terms of time, sample, and space complexity. We prove a Bayesian regret bound under mild assumptions. Our result is more generally applicable to multiple parameters and continuous state action problems. We compare our algorithm with state-of-the-art PSRL algorithms on standard discrete and continuous problems from the literature. Finally, we show how the assumptions of our algorithm satisfy a sensible parametrization for a large class of problems in sequential recommendations.

Keywords

Cite

@article{arxiv.1711.07979,
  title  = {Posterior Sampling for Large Scale Reinforcement Learning},
  author = {Georgios Theocharous and Zheng Wen and Yasin Abbasi-Yadkori and Nikos Vlassis},
  journal= {arXiv preprint arXiv:1711.07979},
  year   = {2018}
}
R2 v1 2026-06-22T22:53:11.152Z