Timezone: »

 
Poster
Scalar Posterior Sampling with Applications
Georgios Theocharous · Zheng Wen · Yasin Abbasi Yadkori · Nikos Vlassis

Wed Dec 05 02:00 PM -- 04:00 PM (PST) @ Room 517 AB #104
in Wed Poster Session B »

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.

Keywords: Bandit Algorithms · Online Learning · Reinforcement Learning and Planning · Recommender Systems
[ Paper] 

Author Information

Georgios Theocharous (Adobe Research)
Zheng Wen (Adobe Research)

Zheng Wen is currently a senior research scientist at Big Data Experience Lab, Adobe Research. His current research focuses on machine learning, operations research, and big data. Before joining Adobe Research, he was a research scientist in Advertising Science Team, Yahoo Labs. Prior to that, he received a Ph.D. in Electrical Engineering from Stanford University.

Yasin Abbasi Yadkori (Adobe Research)
Nikos Vlassis (Netflix)

More from the Same Authors