Linear inverse reinforcement learning in continuous time and space

被引：0

作者：

Kamalapurkar, Rushikesh ^{[1
]}

机构：

[1] Oklahoma State Univ, Sch Mech & Aerosp Engn, Stillwater, OK 74078 USA

来源：

2018 ANNUAL AMERICAN CONTROL CONFERENCE (ACC) | 2018年

关键词：

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper develops a data-driven inverse reinforcement learning technique for a class of linear systems to estimate the cost function of an agent online, using input-output measurements. A simultaneous state and parameter estimator is utilized to facilitate output-feedback inverse reinforcement learning, and cost function estimation is achieved up to multiplication by a constant.

引用

页码：1683 / 1688

页数：6

共 50 条

[21] Linear Reinforcement Learning with Ball Structure Action Space
Jia, Zeyu
Jia, Randy
Madeka, Dhruv
Foster, Dean P.
[J]. INTERNATIONAL CONFERENCE ON ALGORITHMIC LEARNING THEORY, VOL 201, 2023, 201 : 755 - 775
[22] OPTIMAL SCHEDULING OF ENTROPY REGULARIZER FOR CONTINUOUS-TIME LINEAR-QUADRATIC REINFORCEMENT LEARNING
Szpruch, Lukasz
Treetanthiploet, Tanut
Zhang, Yufei
[J]. SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 2024, 62 (01) : 135 - 166
[23] Output Feedback Reinforcement Learning Control for the Continuous-Time Linear Quadratic Regulator Problem
Rizvi, Syed Ali Asad
Lin, Zongli
[J]. 2018 ANNUAL AMERICAN CONTROL CONFERENCE (ACC), 2018, : 3417 - 3422
[24] Robust Inverse Q-Learning for Continuous-Time Linear Systems in Adversarial Environments
Lian, Bosen
Xue, Wenqian
Lewis, Frank L.
Chai, Tianyou
[J]. IEEE TRANSACTIONS ON CYBERNETICS, 2022, 52 (12) : 13083 - 13095
[25] Inverse Reinforcement Learning for Identification in Linear-Quadratic Dynamic Games
Koepf, Florian
Inga, Jairo
Rothfufss, Simon
Flad, Michael
Hohmann, Soeren
[J]. IFAC PAPERSONLINE, 2017, 50 (01): : 14902 - 14908
[26] A state space filter for reinforcement learning in POMDPs - Application to a continuous state space -
Nagayoshi, Masato
Murao, Hajime
Tamaki, Hisashi
[J]. 2006 SICE-ICASE INTERNATIONAL JOINT CONFERENCE, VOLS 1-13, 2006, : 3098 - +
[27] On the Convergence of Reinforcement Learning in Nonlinear Continuous State Space Problems
Goyal, Raman
Chakravorty, Suman
Wang, Ran
Mohamed, Mohamed Naveed Gul
[J]. 2021 60TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2021, : 2969 - 2975
[28] Tree based discretization for continuous state space reinforcement learning
Uther, WTB
Veloso, MM
[J]. FIFTEENTH NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE (AAAI-98) AND TENTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICAL INTELLIGENCE (IAAI-98) - PROCEEDINGS, 1998, : 769 - 774
[29] Experiments of conditioned reinforcement learning in continuous space control tasks
Fernandez-Gauna, Borja
Osa, Juan Luis
Grana, Manuel
[J]. NEUROCOMPUTING, 2018, 271 : 38 - 47
[30] Reinforcement learning in discrete action space applied to inverse defect design
Loeffler, Troy D.
Banik, Suvo
Patra, Tarak K.
Sternberg, Michael
Sankaranarayanan, Subramanian K. R. S.
[J]. JOURNAL OF PHYSICS COMMUNICATIONS, 2021, 5 (03):

← 1 2 3 4 5 →