A Survey of Collaborative Reinforcement Learning: Interactive Methods and Design Patterns

Li, Zhaoxing; Shi, Lei; Cristea, Alexandra I.; Zhou, Yunzhan

Abstract

Recently, methods enabling humans and Artificial Intelligent (AI) agents to collaborate towards improving the efficiency of Reinforcement Learning - also called Collaborative Reinforcement Learning (CRL) - have been receiving increasing attention. In this paper, we provide a long-term, in-depth survey, investigating human-AI collaborative methods based on both interactive reinforcement learning algorithms and human-AI collaborative frameworks, between 2011 and 2020. We elucidate and discuss synergistic analysis methods of both the growth of the field and the state-of-the-art; we suggest novel technical directions and new collaboration design ideas. Specifically, we provide a new CRL classification taxonomy, as a systematic modelling tool for selecting and improving new CRL designs. Furthermore, we propose generic CRL challenges providing the research community with a guide towards effective implementation of human-AI collaboration. The aim is to empower researchers to develop more efficient and natural human-AI collaborative methods that could utilise the different strengths of humans and AI.

Citation

Li, Z., Shi, L., Cristea, A. I., & Zhou, Y. (2023, June). A Survey of Collaborative Reinforcement Learning: Interactive Methods and Design Patterns. Presented at ACM Designing Interactive Systems (DIS), Virtual

• Presentation Conference Type: Conference Paper (published)
• Conference Name: ACM Designing Interactive Systems (DIS)
• Start Date: Jun 28, 2023
• End Date: Jul 2, 2021
• Acceptance Date: Apr 9, 2021
• Online Publication Date: Jun 28, 2021
• Publication Date: 2021
• Deposit Date: Jun 30, 2021
• Publicly Available Date: Jun 30, 2021
• Publisher: Association for Computing Machinery (ACM)
• Pages: 1579-1590
• ISBN: 9781450384766
• DOI: https://doi.org/10.1145/3461778.3462135
• Public URL: https://durham-repository.worktribe.com/output/1140738