SwePub
Sök i LIBRIS databas

  Extended search

onr:"swepub:oai:DiVA.org:kth-338628"
 

Search: onr:"swepub:oai:DiVA.org:kth-338628" > Lambda-Policy Itera...

  • 1 of 1
  • Previous record
  • Next record
  •    To hitlist

Lambda-Policy Iteration with Randomization for Contractive Models with Infinite Policies : Well-Posedness and Convergence

Li, Yuchao (author)
KTH,Reglerteknik
Johansson, Karl H., 1967- (author)
KTH,Reglerteknik
Mårtensson, Jonas, 1976- (author)
KTH,Reglerteknik
 (creator_code:org_t)
ML Research Press, 2020
2020
English.
In: Proceedings of the 2nd Conference on Learning for Dynamics and Control, L4DC 2020. - : ML Research Press. ; , s. 540-549
  • Conference paper (peer-reviewed)
Abstract Subject headings
Close  
  • dynamic programming models are used to analyze λ-policy iteration with randomization algorithms. Particularly, contractive models with infinite policies are considered and it is shown that well-posedness of the λ-operator plays a central role in the algorithm. The operator is known to be well-posed for problems with finite states, but our analysis shows that it is also well-defined for the contractive models with infinite states studied. Similarly, the algorithm we analyze is known to converge for problems with finite policies, but we identify the conditions required to guarantee convergence with probability one when the policy space is infinite regardless of the number of states. Guided by the analysis, we exemplify a data-driven approximated implementation of the algorithm for estimation of optimal costs of constrained linear and nonlinear control problems. Numerical results indicate potentials of this method in practice.

Subject headings

TEKNIK OCH TEKNOLOGIER  -- Elektroteknik och elektronik -- Reglerteknik (hsv//swe)
ENGINEERING AND TECHNOLOGY  -- Electrical Engineering, Electronic Engineering, Information Engineering -- Control Engineering (hsv//eng)
NATURVETENSKAP  -- Matematik -- Beräkningsmatematik (hsv//swe)
NATURAL SCIENCES  -- Mathematics -- Computational Mathematics (hsv//eng)
NATURVETENSKAP  -- Matematik -- Sannolikhetsteori och statistik (hsv//swe)
NATURAL SCIENCES  -- Mathematics -- Probability Theory and Statistics (hsv//eng)

Keyword

approximate dynamic programming
reinforcement learning
λ-policy iteration

Publication and Content Type

ref (subject category)
kon (subject category)

To the university's database

  • 1 of 1
  • Previous record
  • Next record
  •    To hitlist

Find more in SwePub

By the author/editor
Li, Yuchao
Johansson, Karl ...
Mårtensson, Jona ...
About the subject
ENGINEERING AND TECHNOLOGY
ENGINEERING AND ...
and Electrical Engin ...
and Control Engineer ...
NATURAL SCIENCES
NATURAL SCIENCES
and Mathematics
and Computational Ma ...
NATURAL SCIENCES
NATURAL SCIENCES
and Mathematics
and Probability Theo ...
Articles in the publication
By the university
Royal Institute of Technology

Search outside SwePub

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.

 
pil uppåt Close

Copy and save the link in order to return to this view