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

[1] Reinforcement Learning in Continuous Time and Space: A Stochastic Control Approach
Wang, Haoran
Zariphopoulou, Thaleia
Zhou, Xun Yu
[J]. JOURNAL OF MACHINE LEARNING RESEARCH, 2020, 21
[2] Reinforcement learning in continuous time and space: A stochastic control approach
Wang, Haoran
Zariphopoulou, Thaleia
Zhou, Xun Yu
[J]. Journal of Machine Learning Research, 2020, 21
[3] Policy ensemble gradient for continuous control problems in deep reinforcement learning
Liu, Guoqiang
Chen, Gang
Huang, Victoria
[J]. NEUROCOMPUTING, 2023, 548
[4] Reinforcement Learning for Decentralized Stochastic Control
Yongacoglu, Bora
Arslan, Gurdal
Yuksel, Serdar
[J]. 2019 IEEE 58TH CONFERENCE ON DECISION AND CONTROL (CDC), 2019, : 5556 - 5561
[5] Connecting stochastic optimal control and reinforcement learning
Quer, J.
Borrell, Enric Ribera
[J]. JOURNAL OF MATHEMATICAL PHYSICS, 2024, 65 (08)
[6] Reinforcement learning for a class of continuous-time input constrained optimal control problems
Yaghmaie, Farnaz Adib
Braun, David J.
[J]. AUTOMATICA, 2019, 99 : 221 - 227
[7] Improving Stochastic Policy Gradients in Continuous Control with Deep Reinforcement Learning using the Beta Distribution
Chou, Po-Wei
Maturana, Daniel
Scherer, Sebastian
[J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 70, 2017, 70
[8] Continuous Control with a Combination of Supervised and Reinforcement Learning
Kangin, Dmitry
Pugeault, Nicolas
[J]. 2018 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2018, : 163 - 170
[9] Competitive reinforcement learning in continuous control tasks
Abramson, M
Pachowicz, P
Wechsler, H
[J]. PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS 2003, VOLS 1-4, 2003, : 1909 - 1914
[10] Benchmarking Deep Reinforcement Learning for Continuous Control
Duan, Yan
Chen, Xi
Houthooft, Rein
Schulman, John
Abbeel, Pieter
[J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 48, 2016, 48

← 1 2 3 4 5 →