Monte Carlo Tree Search with macro-actions and heuristic route planning for the Physical Travelling Salesman Problem
Monte Carlo Tree Search with macro-actions and heuristic route planning for the Physical Travelling Salesman Problem
复制标题
蒙特卡罗树搜索与宏观行动和启发式路线规划用于物理旅行推销员问题
DOI:
10.1109/cig.2012.6374161
复制
发表时间:
2012
期刊:
影响因子:
--
通讯作者:
Powley E
中科院分区:
文献类型:
--
作者:
Powley E
We present a controller for the Physical Travelling Salesman Problem (PTSP), a path planning and steering problem in a simulated continuous real-time domain. Our approach is hierarchical, using domain-specific algorithms and heuristics to plan a coarse-grained route and Monte Carlo Tree Search (MCTS) to plan and steer along fine-grained paths. The MCTS component uses macro-actions to decrease the number of decisions to be made per unit of time and thus drastically reduce the size of the decision tree. Results from the 2012 WCCI PTSP Competition show that this approach significantly and consistently outperforms all other submitted AI controllers, and is competitive with strong human players. Our approach has potential applications to many other problems in movement planning and control, including video games.
登录
查看更多内容
DOI:
--
发表时间:
2010
期刊:
Proceedings of the 2010 IEEE Conference on Computational Intelligence and Games
影响因子:
--
作者:
Spyridon Samothrakis;David Robles;S. Lucas
通讯作者:
S. Lucas
DOI:
--
发表时间:
2013
期刊:
影响因子:
--
作者:
Marc Lanctot;Christopher Wittlinger;M. Winands;N. D. Teuling
通讯作者:
N. D. Teuling
DOI:
--
发表时间:
2012
期刊:
影响因子:
--
作者:
N. D. Teuling;M. Winands
通讯作者:
M. Winands
DOI:
10.1109/cec.2012.6256440
发表时间:
2012
期刊:
--
影响因子:
--
作者:
Perez D
通讯作者:
Perez D
DOI:
--
发表时间:
2010
期刊:
IEEE Trans. Comput. Intell. AI Games
影响因子:
--
作者:
Chang;Martin Müller;O. Teytaud
通讯作者:
O. Teytaud