Uncertainty-Aware Policy Optimization: A Robust, Adaptive Trust Region Approach

被引:0
作者
Queeney, James [1 ]
Paschalidis, Ioannis Ch [1 ]
Cassandras, Christos G. [1 ]
机构
[1] Boston Univ, Div Syst Engn, Boston, MA 02215 USA
来源
THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE | 2021年 / 35卷
关键词
ALGORITHMS;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In order for reinforcement learning techniques to be useful in real-world decision making processes, they must be able to produce robust performance from limited data. Deep policy optimization methods have achieved impressive results on complex tasks, but their real-world adoption remains limited because they often require significant amounts of data to succeed. When combined with small sample sizes, these methods can result in unstable learning due to their reliance on high-dimensional sample-based estimates. In this work, we develop techniques to control the uncertainty introduced by these estimates. We leverage these techniques to propose a deep policy optimization approach designed to produce stable performance even when data is scarce. The resulting algorithm, Uncertainty-Aware Trust Region Policy Optimization, generates robust policy updates that adapt to the level of uncertainty present throughout the learning process.
引用
收藏
页码:9377 / 9385
页数:9
相关论文
共 23 条
[21]   A MULTI-OBJECTIVE ROBUST OPTIMIZATION APPROACH UNDER INTERVAL UNCERTAINTY BASED ON KRIGING AND SUPPORT VECTOR MACHINE [J].
Xie, Tingli ;
Jiang, Ping ;
Zhou, Qi ;
Shu, Leshi ;
Yang, Yang .
PROCEEDINGS OF THE ASME INTERNATIONAL DESIGN ENGINEERING TECHNICAL CONFERENCES AND COMPUTERS AND INFORMATION IN ENGINEERING CONFERENCE, 2018, VOL 2B, 2018,
[22]   Leveraging the Power of Big Data Analytics for Process Scheduling under Uncertainty using a Stochastic Robust Optimization Approach [J].
Ning, Chao ;
You, Fengqi .
28TH EUROPEAN SYMPOSIUM ON COMPUTER AIDED PROCESS ENGINEERING, 2018, 43 :319-324
[23]   A Hybrid Surrogate-Assisted Accelerated Random Search and Trust Region Approach for Constrained Black-Box Optimization [J].
Regis, Rommel G. .
MACHINE LEARNING, OPTIMIZATION, AND DATA SCIENCE (LOD 2021), PT II, 2022, 13164 :162-177