Reinforcement learning for continuous stochastic control problems

被引：0

作者：

Munos, R ^{[1
]}

Bourgine, P ^{[1
]}

机构：

[1] LISC, CEMAGREF, F-92185 Antony, France

来源：

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 10 | 1998年 / 10卷

关键词：

D O I：

暂无

中图分类号：

B84 [心理学]; C [社会科学总论]; Q98 [人类学];

学科分类号：

03 ; 0303 ; 030303 ; 04 ; 0402 ;

摘要：

This paper is concerned with the problem of Reinforcement Learning (RL) for continuous state space and time stochastic control problems. We state the Hamilton-Jacobi-Bellman equation satisfied by the value function and use a Finite-Difference method for designing a convergent approximation scheme. Then we propose a RL algorithm based on this scheme and prove its convergence to the optimal solution.

引用

页码：1029 / 1035

页数：7

共 50 条

[31] Deep Reinforcement Learning for Continuous Control of Material Thickness
Dippel, Oliver
Lisitsa, Alexei
Peng, Bei
[J]. ARTIFICIAL INTELLIGENCE XL, AI 2023, 2023, 14381 : 321 - 334
[32] Action Robust Reinforcement Learning and Applications in Continuous Control
Tessler, Chen
Efroni, Yonathan
Mannor, Shie
[J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 97, 2019, 97
[33] Stochastic Reinforcement Learning
Kuang, Nikki Lijing
Leung, Clement H. C.
Sung, Vienne W. K.
[J]. 2018 IEEE FIRST INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND KNOWLEDGE ENGINEERING (AIKE), 2018, : 244 - 248
[34] LEARNING AUTOMATA IN STOCHASTIC PLANT CONTROL PROBLEMS
LYUBCHIK, LM
POZNYAK, AS
[J]. AUTOMATION AND REMOTE CONTROL, 1974, 35 (05) : 777 - 789
[35] Advantages of cooperation between reinforcement learning agents in difficult stochastic problems
Berenji, HR
Vengerov, D
[J]. NINTH IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS (FUZZ-IEEE 2000), VOLS 1 AND 2, 2000, : 871 - 876
[36] A phased reinforcement learning algorithm for complex control problems
Goto, Takakuni
Homma, Noriyasu
Yoshizawa, Makoto
Abe, Kenichi
[J]. ARTIFICIAL LIFE AND ROBOTICS, 2007, 11 (02) : 190 - 196
[37] Novel reinforcement learning approach for difficult control problems
Becus, GA
Thompson, EA
[J]. INTELLIGENT ROBOTS AND COMPUTER VISION XVI: ALGORITHMS, TECHNIQUES, ACTIVE VISION, AND MATERIALS HANDLING, 1997, 3208 : 150 - 161
[38] An introduction to stochastic control theory, path integrals and reinforcement learning
Kappen, Hilbert J.
[J]. COOPERATIVE BEHAVIOR IN NEURAL SYSTEMS, 2007, 887 : 149 - 181
[39] Reinforcement Learning for Bio-Inspired Stochastic Robot Control
Gillespie, James
Rano, Inaki
Santos, Jose
Siddique, Nazmul
[J]. 2023 31ST IRISH CONFERENCE ON ARTIFICIAL INTELLIGENCE AND COGNITIVE SCIENCE, AICS, 2023,
[40] Learning Continuous Control Policies by Stochastic Value Gradients
Heess, Nicolas
Wayne, Greg
Silver, David
Lillicrap, Timothy
Tassa, Yuval
Erez, Tom
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 28 (NIPS 2015), 2015, 28

← 1 2 3 4 5 →