Solving Continual Combinatorial Selection via Deep Reinforcement Learning

We consider the Markov Decision Process (MDP) of selecting a subset of items at each step, termed the Select-MDP (S-MDP). The large state and action spaces of S-MDPs make them intractable to solve with typical reinforcement learning (RL) algorithms especially when the number of items is huge. In thi...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-09
Main Authors: Song, Hyungseok, Jang, Hyeryung, Tran, Hai H, Se-eun Yoon, Son, Kyunghwan, Yun, Donggyu, Chung, Hyoju, Yung, Yi
Format: Article
Language:English
Subjects:
Algorithms
Combinatorial analysis
Machine learning
Markov analysis
Markov processes
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We consider the Markov Decision Process (MDP) of selecting a subset of items at each step, termed the Select-MDP (S-MDP). The large state and action spaces of S-MDPs make them intractable to solve with typical reinforcement learning (RL) algorithms especially when the number of items is huge. In this paper, we present a deep RL algorithm to solve this issue by adopting the following key ideas. First, we convert the original S-MDP into an Iterative Select-MDP (IS-MDP), which is equivalent to the S-MDP in terms of optimal actions. IS-MDP decomposes a joint action of selecting K items simultaneously into K iterative selections resulting in the decrease of actions at the expense of an exponential increase of states. Second, we overcome this state space explo-sion by exploiting a special symmetry in IS-MDPs with novel weight shared Q-networks, which prov-ably maintain sufficient expressive power. Various experiments demonstrate that our approach works well even when the item space is large and that it scales to environments with item spaces different from those used in training.
ISSN:2331-8422
DOI:10.48550/arxiv.1909.03638