Reward-Biased Maximum Likelihood Estimation for Linear Stochastic Bandits

Abstract

Modifying the reward-biased maximum likelihood method originally proposed in the adaptive control literature, we propose novel learning algorithms to handle the explore-exploit trade-off in linear bandits problems as well as generalized linear bandits problems. We develop novel index policies that we prove achieve order-optimality, and show that they achieve empirical performance competitive with the state-of-the-art benchmark methods in extensive experiments. The new policies achieve this with low computation time per pull for linear bandits, and thereby resulting in both favorable regret as well as computational efficiency.

References in corpus (5)

• A Contextual-Bandit Approach to Personalized News Article Recommendation
• Thompson Sampling for Contextual Bandits with Linear Payoffs
• Provably Optimal Algorithms for Generalized Linear Contextual Bandits
• Online Stochastic Linear Optimization under One-bit Feedback
• Bayesian bandits: balancing the exploration-exploitation tradeoff via double sampling

Cited by in corpus (1)

• Reward Biased Maximum Likelihood Estimation for Reinforcement Learning