浏览全部资源
扫码关注微信
1. 苏州科技大学电子与信息工程学院,江苏 苏州 215009
2. 苏州科技大学江苏省建筑智慧节能重点实验室,江苏 苏州 215009
3. 苏州科技大学苏州市移动网络技术与应用重点实验室,江苏 苏州 215009
4. 苏州科技大学苏州市虚拟现实智能交互及应用技术重点实验室,江苏 苏州 215009
5. 苏州大学计算机科学与技术学院,江苏 苏州 215006
[ "陈建平(1963−),男,江苏南京人,博士,苏州科技大学教授,主要研究方向为大数据分析与应用、建筑节能、智能信息处理。" ]
[ "何超(1993−),男,江苏徐州人,苏州科技大学硕士生,主要研究方向为强化学习、深度学习、建筑节能。" ]
[ "刘全(1969−),男,内蒙古牙克石人,博士,苏州大学教授、博士生导师,主要研究方向为智能信息处理、自动推理与机器学习。" ]
[ "吴宏杰(1977−),男,江苏苏州人,博士,苏州科技大学副教授,主要研究方向为深度学习、模式识别、生物信息。" ]
[ "胡伏原(1978−),男,湖南岳阳人,博士,苏州科技大学教授,主要研究方向为模式识别与机器学习。" ]
[ "傅启明(1985−),男,江苏淮安人,博士,苏州科技大学讲师,主要研究方向为强化学习、深度学习及建筑节能。" ]
网络出版日期:2018-11,
纸质出版日期:2018-11-25
移动端阅览
陈建平, 何超, 刘全, 等. 增强型深度确定策略梯度算法[J]. 通信学报, 2018,39(11):106-115.
Jianping CHEN, Chao HE, Quan LIU, et al. Enhanced deep deterministic policy gradient algorithm[J]. Journal on communications, 2018, 39(11): 106-115.
陈建平, 何超, 刘全, 等. 增强型深度确定策略梯度算法[J]. 通信学报, 2018,39(11):106-115. DOI: 10.11959/j.issn.1000-436x.2018238.
Jianping CHEN, Chao HE, Quan LIU, et al. Enhanced deep deterministic policy gradient algorithm[J]. Journal on communications, 2018, 39(11): 106-115. DOI: 10.11959/j.issn.1000-436x.2018238.
针对深度确定策略梯度算法收敛速率较慢的问题,提出了一种增强型深度确定策略梯度(E-DDPG)算法。该算法在深度确定策略梯度算法的基础上,重新构建两个新的样本池——多样性样本池和高误差样本池。在算法执行过程中,训练样本分别从多样性样本池和高误差样本池按比例选取,以兼顾样本多样性以及样本价值信息,提高样本的利用效率和算法的收敛性能。此外,进一步从理论上证明了利用自模拟度量方法对样本进行相似性度量的合理性,建立值函数与样本相似性之间的关系。将E-DDPG算法以及DDPG算法用于经典的Pendulum问题和MountainCar问题,实验结果表明,E-DDPG具有更好的收敛稳定性,同时具有更快的收敛速率。
With the problem of slow convergence for deep deterministic policy gradient algorithm
an enhanced deep deterministic policy gradient algorithm was proposed.Based on the deep deterministic policy gradient algorithm
two sample pools were constructed
and the time difference error was introduced.The priority samples were added when the experience was played back.When the samples were trained
the samples were selected from two sample pools respectively.At the same time
the bisimulation metric was introduced to ensure the diversity of the selected samples and improve the convergence rate of the algorithm.The E-DDPG algorithm was used to pendulum problem.The experimental results show that the E-DDPG algorithm can effectively improve the convergence performance of the continuous action space problems and have better stability.
SUTTON R S , BARTO G A . Reinforcement learning:an introduction [M ] . Cambridge : MIT pressPress , 1998 .
朱斐 , 刘全 , 傅启明 , 等 . 一种用于连续动作空间的最小二乘行动者-评论家方法 [J ] . 计算机研究与发展 , 2014 , 51 ( 3 ): 548 - 558 .
ZHU F , LIU Q , FU Q M . A least square actor-critic approach for continuous action space [J ] . Journal of Computer Research and Development , 2014 , 51 ( 3 ): 548 - 558 .
孙志军 , 薛磊 , 许阳明 , 等 . 深度学习研究综述 [J ] . 计算机应用研究 , 2012 , 29 ( 8 ): 2806 - 2810 .
SUN Z J , XUE L , XU Y M , et al . Overview of deep learning [J ] . Application Research of Computers , 2012 , 29 ( 8 ): 2806 - 2810 .
LECUN Y , BENGIO Y , HINTON G . Deep learning [J ] . Nature , 2015 , 521 ( 7553 ): 436 - 444 .
HINTON G E , OSINDERO S , TEH Y W . A fast learning algorithm for deep belief nets [J ] . Neural Computation , 2006 , 18 ( 7 ): 1527 - 1554 .
SILVER D , HUANG A , MADDISON C J , et al . Mastering the game of Go with deep neural networks and tree search [J ] . Nature , 2016 , 529 ( 7587 ): 484 - 489 .
SILVER D , SCHRITTWIESER J , SIMONYAN K , et al . Mastering the game of go without human knowledge [J ] . Nature , 2017 , 550 ( 7676 ): 354 - 359 .
MNIH V , KAVUKCUOFLU K , SILVER D , et al . Playing atari with deep reinforcement learning [C ] // Workshops at the 26th Neural Information Processing Systems . 2013 .
MNIH V , KAVUKCUOFLU K , SILVER D , et al . Human-level control through deep reinforcement learning [J ] . Nature , 2015 , 518 ( 7540 ): 529 - 533 .
WATKINS C J C H . Learning from delayed rewards [J ] . Robotics and Autonomous Systems , 1989 , 15 ( 4 ): 233 - 235 .
VAN H V , GUEZ A , SILVER D . Deep reinforcement learning with double q-learning [C ] // The AAAI Conference on Artificial Intelligence . 2016 .
HASSELT H V , . Double Q-learning [C ] // The Advances in Neural Information Processing Systems . 2010 .
SCHAUL T , QUAN J , ANTONOGLOU I , et al . Prioritized experience replay [C ] // The 4th International Conference on Learning Representations . 2016 : 322 - 355 .
SUTTON R S , MCALLESTER D , SINGH S , et al . Policy gradient methods for reinforcement learning with function approximation [J ] . Advances in Neural Information Processing Systems , 2000 , 12 : 1057 - 1063 .
LILLICRAP T P , HUNT J J , PRITZEL A , et al . Continuous control with deep reinforcement learning [C ] // The 4th International Conference on Learning Representations . 2015 .
SILVER D , LEVER G , HEESS N , et al . Deterministic policy gradient algorithms [C ] // The International Conference on Machine Learning . 2014 .
GIVAN R , DEAN T , GREIG M . Equivalence notions and model minimization in Markov decision processes [J ] . Artificial Intelligence , 2003 , 147 ( 1-2 ): 163 - 223 .
FERNS N , PANANGADEN P , PRECUP D . Metrics for finite markov decision processes [C ] // The 20th Conference on Uncertainty in Artificial Intelligence . 2004 .
0
浏览量
1468
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构