.png){kind=icon}
返回
A temporal difference method for multi-objective reinforcement learning
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2016.10.100.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This work describes MPQ-learning, an algorithm that approximates the set of all deterministic non dominated policies in multi-objective Markov decision problems, where rewards are vectors and each component stands for an objective to maximize. MPQ-learning generalizes directly the ideas of Q-learning to the multi-objective case. It can be applied to non-convex Pareto frontiers and finds both supported and unsupported solutions. We present the results of the application of MPQ-learning to some benchmark problems. The algorithm solves successfully these problems, so showing the feasibility of this approach. We also compare MPQ-learning to a standard linearization procedure that computes only supported solutions and show that in some cases MPQ-learning can be as effective as the scalarization method. (C) 2017 Elsevier B.V. All rights reserved.
Keyword:
Reinforcement learning
Multi-objective optimization
MOMDPs
Q-leaming
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Deficient cerebellar long-term depression and impaired motor learning in mGluR1 mutant mice.png)
Cell
CellIF0
PREAI
分享收藏分享收藏Empirical evaluation methods for multiobjective reinforcement learning algorithmsMACHINE LEARNING
OAAI
MACHINE LEARNINGIF2.9
OAAI分享收藏Hypervolume indicator and dominance reward based multi-objective Monte-Carlo Tree SearchMACHINE LEARNINGOAAI
MACHINE LEARNINGIF2.9
OAAI分享收藏Reinforcement learning based sensing policy optimization for energy efficient cognitive radio networksNEUROCOMPUTINGOAAI
NEUROCOMPUTINGIF6.5
OAAI分享收藏 没有更多内容
没有更多内容