期刊文献+

A model-based approximate λ-policy iteration approach to online evasive path planning and the video game Ms.Pac-Man

A model-based approximate λ-policy iteration approach to online evasive path planning and the video game Ms.Pac-Man
原文传递
导出
摘要 This paper presents a model-based approximate λ-policy iteration approach using temporal differences for optimizing paths online for a pursuit-evasion problem,where an agent must visit several target positions within a region of interest while simultaneously avoiding one or more actively pursuing adversaries.This method is relevant to applications,such as robotic path planning,mobile-sensor applications,and path exposure.The methodology described utilizes cell decomposition to construct a decision tree and implements a temporal difference-based approximate λ-policy iteration to combine online learning with prior knowledge through modeling to achieve the objectives of minimizing the risk of being caught by an adversary and maximizing a reward associated with visiting target locations.Online learning and frequent decision tree updates allow the algorithm to quickly adapt to unexpected movements by the adversaries or dynamic environments.The approach is illustrated through a modified version of the video game Ms.Pac-Man,which is shown to be a benchmark example of the pursuit-evasion problem.The results show that the approach presented in this paper outperforms several other methods as well as most human players. This paper presents a model-based approximate λ-policy iteration approach using temporal differences for optimizing paths online for a pursuit-evasion problem,where an agent must visit several target positions within a region of interest while simultaneously avoiding one or more actively pursuing adversaries.This method is relevant to applications,such as robotic path planning,mobile-sensor applications,and path exposure.The methodology described utilizes cell decomposition to construct a decision tree and implements a temporal difference-based approximate λ-policy iteration to combine online learning with prior knowledge through modeling to achieve the objectives of minimizing the risk of being caught by an adversary and maximizing a reward associated with visiting target locations.Online learning and frequent decision tree updates allow the algorithm to quickly adapt to unexpected movements by the adversaries or dynamic environments.The approach is illustrated through a modified version of the video game Ms.Pac-Man,which is shown to be a benchmark example of the pursuit-evasion problem.The results show that the approach presented in this paper outperforms several other methods as well as most human players.
出处 《控制理论与应用(英文版)》 EI 2011年第3期391-399,共9页
基金 supported by the National Science Foundation (No.ECS 0925407)
关键词 Approximate dynamic programming Reinforcement learning Path planning Pursuit evasion games Approximate dynamic programming Reinforcement learning Path planning Pursuit evasion games
  • 相关文献

参考文献18

  • 1A. Nedi?,D. P. Bertsekas.Least Squares Policy Evaluation Algorithms with Linear Function Approximation[J]. Discrete Event Dynamic Systems . 2003 (1-2)
  • 2Seapahn Megerian,Farinaz Koushanfar,Gang Qu,Giacomino Veltri,Miodrag Potkonjak.Exposure in Wireless Sensor Networks: Theory and Practical Solutions[J]. Wireless Networks . 2002 (5)
  • 3K. Kedem,M. Sharir.An efficient motion-planning algorithm for a convex polygonal object in two-dimensional polygonal space[J]. Discrete & Computational Geometry . 1990 (1)
  • 4V. Phipatanasuphorn,,P. Ramanathan.Vulnerability of sensor networks to unauthorized traversal and monitoring. IEEE Transactions on Computers . 2004
  • 5S. Lucas.Evolving a neural network location evaluator to play ms. pacman. Proceedings of the 2005 IEEE Symposium on Computational Intelligence and Games . 2005
  • 6P. Burrow,,S. Lucas.Evolution versus temporal difference learning for learning to play ms. pac-man. Proceedings of the 5th International Conference on Computational Intelligence and Games . 2009
  • 7L. DeLooze,,W. Viner.Fuzzy Q-learning in a nondeterministic environment: developing an intelligent ms. pac-man agent. Proceedings of the 5th International Conference on Computational Intelligence and Games . 2009
  • 8M. Emilio,,M. Moises,,R. Gustavo,et al.Pacman: Optimization based on ant colonies applied to developing an agent for ms. pac-man. Proceedings of IEEE Conference on Computational Intelligence and Games . 2010
  • 9R. Thawonmas,,T. Ashida.Evolution strategy for optimizing parameters in ms. pacman controller ice pambrush 3. Proceedings of IEEE Conference on Computational Intelligence and Games . 2010
  • 10D. P. Bertsekas,,S. Ioffe.Temporal Differences-based Policy Iteration and Applications in Neuro-dynamic Programming. Report LIDS-P- 2349 . 1996

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部