Publication - Efficient Multi-Agent Reinforcement Learning through Automated Supervision
Authors: | Zhang, Chongjie; Abdallah, Sherief; Lesser, Victor | ||||
Title: | Efficient Multi-Agent Reinforcement Learning through Automated Supervision | ||||
Abstract: | Multi-Agent Reinforcement Learning (MARL) algorithms suffer from slow convergence and even divergence, especially in large-scale systems. In this work, we develop a supervision framework to speed up the convergence of MARL algorithms in a network of agents. The framework defines an organizational structure for automated supervision and a communication protocol for exchanging information between lower-level agents and higher-level supervising agents. The abstracted states of lower-level agents travel upwards so that higher-level supervising agents generate a broader view of the state of the network. This broader view is used in creating supervisory information which is passed down the hierarchy. We present a generic extension to MARL algorithms that integrates supervisory information into the learning process, guiding agents' exploration of their state-action space. | ||||
Keywords: | Communication Protocol, Distributed AI, Learning, Multi-Agent Systems | ||||
Publication: | Proceedings of the Seventh International Conference on Autonomous Agents and Multiagent Systems, pp. 1365 - 1368 | ||||
Editor: | Padgham, Parkes, Müller and Parsons | ||||
Location: | Estoril, Portugal | ||||
Publisher: | IFMAAS | ||||
Date: | 2008 | ||||
Sources: |
PDF: /Documents/cjzhang/czhang_aamas08.pdf |
||||
Notes: | (Short paper) | ||||
Reference: | Zhang, Chongjie; Abdallah, Sherief; Lesser, Victor. Efficient Multi-Agent Reinforcement Learning through Automated Supervision. Proceedings of the Seventh International Conference on Autonomous Agents and Multiagent Systems, Padgham, Parkes, Müller and Parsons, ed., IFMAAS, pp. 1365-1368. 2008. (Short paper) | ||||
bibtex: | @inproceedings{Zhang-451, author = "Chongjie Zhang and Sherief Abdallah and Victor Lesser", title = "{Efficient Multi-Agent Reinforcement Learning through Automated Supervision}", booktitle = "Proceedings of the Seventh International Conference on Autonomous Agents and Multiagent Systems", editor = "Parkes Padgham and ller Mu\̈ and Parsons", publisher = "IFMAAS", pages = "1365-1368", year = "2008", address = "Estoril, Portugal", url = "http://mas.cs.umass.edu/paper/451", } |