This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Application of Multi-Agent Reinforcement Learning to RLSS Material Circulation Control System
Technical Paper
2004-01-2437
ISSN: 0148-7191, e-ISSN: 2688-3627
Annotation ability available
Sector:
Language:
English
Abstract
A Regenerative Life Support System (RLSS) is a system that establishes self-sustained material recycling and circulation within a space base on the Moon or Mars. This is a large-scale and complicated system comprising a lot of components such as humans, plants and material circulation system. A RLSS contains many factors with uncertainty, such as dynamics of plants and humans, and failure and performance deterioration of devices. In addition, a RLSS is a large-scale and complicated system extending gradually. An environment with uncertainty or a large-scale and complicated system may not be properly addressed by a centralized system. In particular, such a system cannot always gather accurate information in one center in a frequently shifting environment, thus appropriate processing may be difficult. Therefore, we tried autonomous decentralization of information or decision-making using a Multi-Agent System (MAS). This report discuss the designing of a RLSS material circulation control system using a MAS and a method in which a MAS acquires cooperative action in a bottom-up approach by means of computer simulation. So far, we have confirmed the effectiveness of this method for a RLSS material circulation control system and proved that automatic acquisition of cooperation rules with the autonomous learning among agents are enabled.
Recommended Content
Citation
Miyajima, H., Hirosaki, T., and Ishikawa, Y., "Application of Multi-Agent Reinforcement Learning to RLSS Material Circulation Control System," SAE Technical Paper 2004-01-2437, 2004, https://doi.org/10.4271/2004-01-2437.Also In
References
- Takadama, K. Multiagent Learning Exploring Potentials Embedded in Interaction among Agents Corona Publishing 2003
- Hirosaki, T. Yamauchi, N. Yoshida, H. Ishikawa, Y. Miyajima: H. Application of Multi-agent Reinforcement Learning to CELSS Material Circulation Control PAIS2001 Conference Proceedings 2001
- Sutton R. S. Barto A. G. Reinforcement Learning - Introduction A Bradford Book The MIT Press 1998
- Kimura, H. Miyazaki K. Kobayashi, S. Design Manual for Reinforcement Learning System Journal of the SICE 38 No. 10 1999
- Arai, S. Miyazaki K. Kobayashi, S. Methodology in Multi-Agent Reinforcement Learning – Approach by Q-Learning and Profit Sharing Transactions of the Japanese Society for Artificial Intelligence 13 No. 4 1998
- Miyajima, H. Abe, K. Ishikawa, Y. Ashida A. Nitta, K. Simulation to Support an Integration Test Project of CEEF SAE 2001-01-2130 2001
- Aoki, K. Kimura, H. Kobayashi, S. Cooperative control of sewage systems using distributed Reinforcement Learning Proceeding of 30th SICE Symposium on Intelligent Systems 2003