GeezerVisonThe World Wide Web, restored to 800 pixels of glory. |
| Home|About|Gaming cabinet|Archives|How it works|Starter sites |
GeezerVison is showing research.google — SlateQ: A Tractable Decomposition for Reinforcement Learning with Recommendation Sets SlateQ: A Tractable Decomposition for Reinforcement Learning with Recommendation Sets
Vihan Jain
Jing Wang
Sanmit Narvekar
Ritesh Agarwal
Rui Wu
Proceedings of the Twenty-eighth International Joint Conference on Artificial Intelligence (IJCAI-19), Macau, China (2019), pp. 2592-2599
Abstract
Reinforcement learning (RL) methods for recommender systems optimize recommendations for long-term user engagement. However, since users are often presented with slates of multiple items---which may have interacting effects on user choice---methods are required to deal with the combinatorics of the RL action space. We develop SlateQ, a decomposition of value-based temporal-difference and Q-learning that renders RL tractable with slates. Under mild assumptions on user choice behavior, we show that the long-term value (LTV) of a slate can be decomposed into a tractable function of its component item-wise LTVs. We demonstrate our methods in simulation, and validate the scalability and effectiveness of decomposed TD-learning on YouTube.
Research AreasMeet the teams driving innovationOur teams advance the state of the art through research, systems engineering, and collaboration across Google. See our teams
|
| You are visitor 01402503 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required. |