Computer Science and Information Engineering, World Congress on (2009)
Los Angeles, California USA
Mar. 31, 2009 to Apr. 2, 2009
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/CSIE.2009.234
Multi-agent simulation system based on reinforcement learning algorithm is a micro-individual acts of modeling and simulation methods, which have wide applicability, distribution, intelligent and interactive features etc. Firstly, studying on reinforcement learning algorithm, and then analysis and design the multi-agent simulation system structure, multi-agent system main modules, the implementation of the definition and finally, carefully design the multi-agent simulation system software, and multi-agent simulation collective system simulation and surrounded the location gathered from the space simulation experiment, the results showed that: Construct a multi-agent simulation system based on reinforcement learning algorithm, achieve real-time simulation of multi-agene, and multi-agent to get effect quickly, and to quickly construct surrounded conduct by mobile groups, the conduct of the system to achieve the global optimum effect.
reinforcement learning, multi-agent simulation, collective siege, gathered from space
S. N. Wang, S. D. Wang and W. P. Zhang, "Study on Multi-agent Simulation System Based on Reinforcement Learning Algorithm," 2009 WRI World Congress on Computer Science and Information Engineering, CSIE(CSIE), Los Angeles, CA, 2009, pp. 523-527.