Sökning: onr:"swepub:oai:DiVA.org:kth-338628" >
Lambda-Policy Itera...
Lambda-Policy Iteration with Randomization for Contractive Models with Infinite Policies : Well-Posedness and Convergence
-
- Li, Yuchao (författare)
- KTH,Reglerteknik
-
- Johansson, Karl H., 1967- (författare)
- KTH,Reglerteknik
-
- Mårtensson, Jonas, 1976- (författare)
- KTH,Reglerteknik
-
(creator_code:org_t)
- ML Research Press, 2020
- 2020
- Engelska.
-
Ingår i: Proceedings of the 2nd Conference on Learning for Dynamics and Control, L4DC 2020. - : ML Research Press. ; , s. 540-549
- Relaterad länk:
-
http://proceedings.m...
-
visa fler...
-
https://urn.kb.se/re...
-
visa färre...
Abstract
Ämnesord
Stäng
- 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.
Ämnesord
- 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)
Nyckelord
- approximate dynamic programming
- reinforcement learning
- λ-policy iteration
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)