Search: id:"swepub:oai:research.chalmers.se:6f91ddb5-484d-4cd7-9591-ddbc27f7b0ba" >
Reinforcement Learn...
Reinforcement Learning Informed by Optimal Control
-
- Önnheim, Magnus, 1985 (author)
- Göteborgs universitet,University of Gothenburg,Chalmers tekniska högskola,Chalmers University of Technology
-
- Andersson, Pontus, 1995 (author)
- Chalmers tekniska högskola,Chalmers University of Technology,Göteborgs universitet,University of Gothenburg
-
- Gustavsson, Emil, 1987 (author)
- Göteborgs universitet,University of Gothenburg,Chalmers tekniska högskola,Chalmers University of Technology
-
show more...
-
- Jirstrand, Mats, 1968 (author)
- Chalmers tekniska högskola,Chalmers University of Technology,Göteborgs universitet,University of Gothenburg
-
show less...
-
(creator_code:org_t)
- 2019-09-09
- 2019
- English.
-
In: Lecture Notes in Computer Science. - Cham : Springer International Publishing. - 0302-9743 .- 1611-3349. ; 11731, s. 403-407
- Related links:
-
https://research.cha...
-
show more...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- Model-free reinforcement learning has seen tremendous advances in the last few years, however practical applications of pure reinforcement learning are still limited by sample inefficiency and the difficulty of giving robustness and stability guarantees of the proposed agents. Given access to an expert policy, one can increase sample efficiency by in addition to learning from data, and also learn from the experts actions for safer learning. In this paper we pose the question whether expert learning can be accelerated and stabilized if given access to a family of experts which are designed according to optimal control principles, and more specifically, linear quadratic regulators. In particular we consider the nominal model of a system as part of the action space of a reinforcement learning agent. Further, using the nominal controller, we design customized reward functions for training a reinforcement learning agent, and perform ablation studies on a set of simple benchmark problems.
Subject headings
- SAMHÄLLSVETENSKAP -- Utbildningsvetenskap -- Lärande (hsv//swe)
- SOCIAL SCIENCES -- Educational Sciences -- Learning (hsv//eng)
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Reglerteknik (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Control Engineering (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Keyword
- Adaptive control
- Expert learning
- Optimal control
- Linear quadratic control
- Reinforcement learning
- Online learning
Publication and Content Type
- kon (subject category)
- ref (subject category)
Find in a library
To the university's database