id:"swepub:oai:DiVA.org:liu-53354"
Search: id:"swepub:oai:DiVA.org:liu-53354" > Greedy adaptive cri...
- 1 of 1
- Previous record
- Next record
- To hitlist
- Landelius, Tomasn/a (author)
Greedy adaptive critics for LPQ [dvs LQR] problems : Convergence Proofs
- BookEnglish1996
Publisher, publication year, extent ...
- Linköping, Sweden :Linköping University, Department of Electrical Engineering,1996
- 20 s.
- electronicrdacarrier
Numbers
- LIBRIS-ID:oai:DiVA.org:liu-53354
- https://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-53354URI
Supplementary language notes
- Language:English
- Summary in:English
Part of subdatabase
- SwePubSwePub
Classification
Series
- LiTH-ISY-R,1400-3902 ;1896
Notes
- A number of success stories have been told where reinforcement learning has been applied to problems in continuous state spaces using neural nets or other sorts of function approximators in the adaptive critics. However, the theoretical understanding of why and when these algorithms work is inadequate. This is clearly exemplified by the lack of convergence results for a number of important situations. To our knowledge only two such results been presented for systems in the continuous state space domain. The first is due to Werbos and is concerned with linear function approximation and heuristic dynamic programming. Here no optimal strategy can be found why the result is of limited importance. The second result is due to Bradtke and deals with linear quadratic systems and quadratic function approximators. Bradtke's proof is limited to ADHDP and policy iteration techniques where the optimal solution is found by a number of successive approximations. This paper deals with greedy techniques, where the optimal solution is directly aimed for. Convergence proofs for a number of adaptive critics, HDP, DHP, ADHDP and ADDHP, are presented. Optimal controllers for linear quadratic regulation (LQR) systems can be found by standard techniques from control theory but the assumptions made in control theory can be weakened if adaptive critic techniques are employed. The main point of this paper is, however, not to emphasize the differences but to highlight the similarities and by so doing contribute to a theoretical understanding of adaptive critics.
Subject headings and genre
- Linear quadratic regulation
- Reinforcement learning
- TECHNOLOGY
- TEKNIKVETENSKAP
Added entries (persons, corporate bodies, meetings, titles ...)
- Knutsson, HansLinköpings universitet,Bildbehandling,Tekniska högskolan(Swepub:liu)hankn25 (author)
- n/aBildbehandling (creator_code:org_t)
Internet link
To the university's database
- 1 of 1
- Previous record
- Next record
- To hitlist
Find more in SwePub
- By the author/editor
- Landelius, Tomas
- Knutsson, Hans
- Parts in the series
- LiTH-ISY-R,
- By the university
- Linköping University
Search outside SwePub
- Extend your search to:
- Google Book Search
- Google Scholar
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.
- Copyright © LIBRIS - National Library Systems
- LIBRIS.kb.se
