arxivst stuff from arxiv that you should probably bookmark

Value Directed Exploration in Multi-Armed Bandits with Structured Priors

Abstract · Apr 12, 2017 20:46 ·

lookahead structured arms actions bandit discounts ucb reward armed cs-lg cs-ai stat-ml

Arxiv Abstract

  • Bence Cserna
  • Marek Petrik
  • Reazul Hasan Russel
  • Wheeler Ruml

Multi-armed bandits are a quintessential machine learning problem requiring the balancing of exploration and exploitation. While there has been progress in developing algorithms with strong theoretical guarantees, there has been less focus on practical near-optimal finite-time performance. In this paper, we propose an algorithm for Bayesian multi-armed bandits that utilizes value-function-driven online planning techniques. Building on previous work on UCB and Gittins index, we introduce linearly-separable value functions that take both the expected return and the benefit of exploration into consideration to perform n-step lookahead. The algorithm enjoys a sub-linear performance guarantee and we present simulation results that confirm its strength in problems with structured priors. The simplicity and generality of our approach makes it a strong candidate for analyzing more complex multi-armed bandit problems.

Read the paper (pdf) »