RecSim: A Configurable Simulation Platform for Recommender Systems

2019/09/11 by Eugene Ie, Ie, Eugene, Chih‐Wei Hsu +13 · 6 citations
Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #Artificial Intelligence in Games #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #Information Retrieval (cs.IR) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Reinforcement Learning in Robotics

paper · pdf · doi:10.48550/arxiv.1909.04847

openalex publication_date 2019/09/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Contextual Markov Decision Processes
• A Neural Conversational Model
• Beyond Greedy Ranking: Slate Optimization via List-CVAE
• RecoGym: A Reinforcement Learning Environment for the problem of Product\n Recommendation in Online Advertising
• Soft Actor-Critic Algorithms and Applications
• Challenges of Real-World Reinforcement Learning
• TensorFlow: A system for large-scale machine learning
• Toward Simulating Environments in Reinforcement Learning Based\n Recommendations

Cited by

• Selecting User Histories to Generate LLM Users for Cold-Start Item Recommendation
• Beyond Action Imitation: Learning a Decision-Aware User Simulator for Online Advertising
• Mirroring Users: Towards Building Preference-aligned User Simulator with User Feedback in Recommendation
• Informfully Recommenders -- Reproducibility Framework for Diversity-aware Intra-session Recommendations
• Diagnostic-Guided Dynamic Profile Optimization for LLM-based User Simulators in Sequential Recommendation
• RecoMind: A Reinforcement Learning Framework for Optimizing In-Session User Satisfaction in Recommendation Systems

Related

• RecoWorld: Building Simulated Environments for Agentic Recommender Systems
• KuaiSim: A Comprehensive Simulator for Recommender Systems
• Synthetic Data-Based Simulators for Recommender Systems: A Survey
• RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems
• SARDINE: A Simulator for Automated Recommendation in Dynamic and Interactive Environments