Poster
Scalar Posterior Sampling with Applications
Georgios Theocharous · Zheng Wen · Yasin Abbasi Yadkori · Nikos Vlassis
Room 517 AB #104
Keywords: [ Bandit Algorithms ] [ Online Learning ] [ Reinforcement Learning and Planning ] [ Recommender Systems ]
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 parameterization for a large class of problems in sequential recommendations.