Regret Bounds for Risk-Sensitive Reinforcement Learning

被引：0

作者：

Bastani, Osbert ^{[1
]}

Ma, Yecheng Jason ^{[1
]}

Shen, Estelle ^{[1
]}

Xu, Wanqiao ^{[2
]}

机构：

[1] Univ Penn, Philadelphia, PA 19104 USA

[2] Stanford Univ, Stanford, CA USA

来源：

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35, NEURIPS 2022 | 2022年

关键词：

VALUE-AT-RISK;

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 safety-critical applications of reinforcement learning such as healthcare and robotics, it is often desirable to optimize risk-sensitive objectives that account for tail outcomes rather than expected reward. We prove the first regret bounds for reinforcement learning under a general class of risk-sensitive objectives including the popular CVaR objective. Our theory is based on a novel characterization of the CVaR objective as well as a novel optimistic MDP construction.

引用

页数：11

共 50 条

[31] Risk-sensitive reinforcement learning applied to control under constraints
Geibel, P
Wysotzki, F
JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, 2005, 24 : 81 - 108
[32] Risk-sensitive reinforcement learning applied to control under constraints
Geibel, P. (PGEIBEL@UOS.DE), 1600, American Association for Artificial Intelligence (24):
[33] Risk-Sensitive Portfolio Management by using Distributional Reinforcement Learning
Harnpadungkij, Thammasorn
Chaisangmongkon, Warasinee
Phunchongharn, Phond
2019 IEEE 10TH INTERNATIONAL CONFERENCE ON AWARENESS SCIENCE AND TECHNOLOGY (ICAST 2019), 2019, : 110 - 115
[34] Risk-Sensitive Reinforcement Learning for URLLC Traffic in Wireless Networks
Ben Khalifa, Nesrine
Assaad, Mohamad
Debbah, Merouane
2019 IEEE WIRELESS COMMUNICATIONS AND NETWORKING CONFERENCE (WCNC), 2019,
[35] Bounds for a risk-sensitive homing problem☆
Makasu, Cloud
AUTOMATICA, 2024, 163
[36] Regret Bounds for Learning State Representations in Reinforcement Learning
Ortner, Ronald
Pirotta, Matteo
Fruit, Ronan
Lazaric, Alessandro
Maillard, Odalric-Ambrym
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
[37] Variational Bayesian Reinforcement Learning with Regret Bounds
O'Donoghue, Brendan
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021,
[38] Non-stationary Risk-Sensitive Reinforcement Learning: Near-Optimal Dynamic Regret, Adaptive Detection, and Separation Design
Ding, Yuhao
Jin, Ming
Lavaei, Javad
THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 6, 2023, : 7405 - 7413
[39] Risk-Sensitive Reinforcement Learning Part I: Constrained Optimization Framework
Prashanth, L. A.
2019 FIFTH INDIAN CONTROL CONFERENCE (ICC), 2019, : 9 - 9
[40] Risk-Sensitive Reinforcement Learning Via Entropic-VaR Optimization
Ni, Xinyi
Lai, Lifeng
2022 56TH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS, AND COMPUTERS, 2022, : 953 - 959

← 1 2 3 4 5 →