Affiliation:
1. Okayama University, 3-1-1 Tsushima-naka, Kita-ku, Okayama 700-8530, Japan
Abstract
Multiagent reinforcement learning performs well in multiple situations such as social simulation and data mining. It particularly stands out in robot control. In this approach, artificial agents behave in a system and learn their policies for their own satisfaction and that of others. Robots encode policies to simulate the performance. Therefore, learning should maintain and improve system performance. Previous studies have attempted various approaches to outperform control robots. This paper provides an overview of multiagent reinforcement learning work, primarily on navigation. Specifically, we discuss current achievements and limitations, followed by future challenges.
Publisher
Fuji Technology Press Ltd.
Reference58 articles.
1. S. Thrun, W. Burgard, and D. Fox, “Probabilistic Robotics (Intelligent Robotics and Autonomous Agents),” The MIT Press, 2005.
2. K. J. Singh, A. Nayyar, D. S. Kapoor, N. Mittal, S. Mahajan, A. K. Pandit, and M. Masud, “Adaptive Flower Pollination Algorithm-Based Energy Efficient Routing Protocol for Multi-Robot Systems,” IEEE Access, Vol.9, pp. 82417-82434, 2021. https://doi.org/10.1109/ACCESS.2021.3086628
3. Y. Chang, L. Ballotta, and L. Carlone, “D-Lite: Navigation-Oriented Compression of 3D Scene Graphs for Multi-Robot Collaboration,” IEEE Robotics and Automation Letters, Vol.8, No.11, pp. 7527-7534, 2023. https://doi.org/10.1109/LRA.2023.3320011
4. S. Han, M. Dastani, and S. Wang, “Model-based Sparse Communication in Multi-agent Reinforcement Learning,” Proc. of the 2023 Int. Conf. on Autonomous Agents and Multiagent Systems (AAMAS), pp. 439-447, 2023.
5. G. Sharon, R. Stern, A. Felner, and N. R. Sturtevant, “Conflict-Based Search for Optimal Multi-Agent Pathfinding,” Artificial Intelligence, Vol.219, pp. 40-66, 2015. https://doi.org/10.1016/j.artint.2014.11.006