Yang, Y; Luo, J; Wen, Y; Slumbers, O; Graves, D; Ammar, HB; Wang, J; Yang, Y; Luo, J; Wen, Y; Slumbers, O; Graves, D; Ammar, HB; Wang, J; Taylor, ME; - view fewer (2021) Diverse auto-curriculum is critical for successful real-world multiagent learning systems. In: Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems. (pp. pp. 51-56). Association for Computing Machinery (ACM)

Preview

Text 2102.07659.pdf - Published Version Download (512kB) | Preview

Abstract

Multiagent reinforcement learning (MARL) has achieved a remarkable amount of success in solving various types of video games. A cornerstone of this success is the auto-curriculum framework, which shapes the learning process by continually creating new challenging tasks for agents to adapt to, thereby facilitating the acquisition of new skills. In order to extend MARL methods to real-world domains outside of video games, we envision in this blue sky paper that maintaining a diversity-aware auto-curriculum is critical for successful MARL applications. Specifically, we argue that behavioural diversity is a pivotal, yet under-explored, component for real-world multiagent learning systems, and that significant work remains in understanding how to design a diversity-aware auto-curriculum. We list four open challenges for auto-curriculum techniques, which we believe deserve more attention from this community. Towards validating our vision, we recommend modelling realistic interactive behaviours in autonomous driving as an important test bed, and recommend the SMARTS/ULTRA benchmark.

Download activity - last month

Export as XMLJSONCSV

Download activity - last 12 months

Export as XMLCSVJSON

Downloads by country - last 12 months

Export as JSONCSVXML

Archive Staff Only

View Item