RecSim: A Configurable Simulation Platform for Recommender Systems

TL;DR

RecSim is a flexible simulation platform designed for developing and testing sequential recommender systems, supporting diverse user behaviors and enabling advanced RL research.

Contribution

It introduces a configurable environment platform that models complex user behaviors and interactions, facilitating research in reinforcement learning for recommender systems.

Findings

Supports diverse user and item models

Enables testing of RL algorithms in realistic scenarios

Fosters collaboration between academia and industry

Abstract

We propose RecSim, a configurable platform for authoring simulation environments for recommender systems (RSs) that naturally supports sequential interaction with users. RecSim allows the creation of new environments that reflect particular aspects of user behavior and item structure at a level of abstraction well-suited to pushing the limits of current reinforcement learning (RL) and RS techniques in sequential interactive recommendation problems. Environments can be easily configured that vary assumptions about: user preferences and item familiarity; user latent state and its dynamics; and choice models and other user response behavior. We outline how RecSim offers value to RL and RS researchers and practitioners, and how it can serve as a vehicle for academic-industrial collaboration.