Bayesian Reinforcement Learning with Exploration

被引：0

作者：

Lattimore, Tor ^{[1
]}

Hutter, Marcus ^{[2
]}

机构：

[1] Univ Alberta, Edmonton, AB T6G 2M7, Canada

[2] Australian Natl Univ, Canberra, ACT 0200, Australia

来源：

ALGORITHMIC LEARNING THEORY (ALT 2014) | 2014年 / 8776卷

关键词：

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：

We consider a general reinforcement learning problem and show that carefully combining the Bayesian optimal policy and an exploring policy leads to minimax sample-complexity bounds in a very general class of (history-based) environments. We also prove lower bounds and show that the new algorithm displays adaptive behaviour when the environment is easier than worst-case.

引用

页码：170 / 184

页数：15

共 50 条

[1] Model-based Lifelong Reinforcement Learning with Bayesian Exploration
Fu, Haotian
Yu, Shangqun
Littman, Michael
Konidaris, George
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
[2] Bayesian Optimistic Optimization: Optimistic Exploration for Model-based Reinforcement Learning
Wu, Chenyang
Li, Tianci
Zhang, Zongzhang
Yu, Yang
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
[3] Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis
Mitta, Rohan
Hasanbeig, Hosein
Wang, Jun
Kroening, Daniel
Kantaros, Yiannis
Abate, Alessandro
THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 19, 2024, : 21412 - 21419
[4] Benchmarking for Bayesian Reinforcement Learning
Castronovo, Michael
Ernst, Damien
Couetoux, Adrien
Fonteneau, Raphael
PLOS ONE, 2016, 11 (06):
[5] Bayesian Inverse Reinforcement Learning
Ramachandran, Deepak
Amir, Eyal
20TH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2007, : 2586 - 2591
[6] Bayesian reinforcement learning: A survey
Ghavamzadeh, Mohammad
Mannor, Shie
Pineau, Joelle
Tamar, Aviv
Foundations and Trends in Machine Learning, 2015, 8 (5-6): : 359 - 483
[7] Exploration Entropy for Reinforcement Learning
Xin, Bo
Yu, Haixu
Qin, You
Tang, Qing
Zhu, Zhangqing
MATHEMATICAL PROBLEMS IN ENGINEERING, 2020, 2020
[8] Exploration in Structured Reinforcement Learning
Ok, Jungseul
Proutiere, Alexandre
Tranos, Damianos
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
[9] Exploration and Incentives in Reinforcement Learning
Simchowitz, Max
Slivkins, Aleksandrs
OPERATIONS RESEARCH, 2024, 72 (03) : 983 - 998
[10] Conservative Exploration in Reinforcement Learning
Garcelon, Evrard
Ghavamzadeh, Mohammad
Lazaric, Alessandro
Pirotta, Matteo
INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 108, 2020, 108 : 1431 - 1440

← 1 2 3 4 5 →