Sökning: id:"swepub:oai:DiVA.org:liu-53411" >
Reinforcement Learn...
Reinforcement Learning Trees
-
- Landelius, Tomas (författare)
- n/a
-
- Borga, Magnus (författare)
- Linköpings universitet,Bildbehandling,Tekniska högskolan
-
- Knutsson, Hans (författare)
- Linköpings universitet,Bildbehandling,Tekniska högskolan
-
(creator_code:org_t)
- Linköping, Sweden : Linköping University, Department of Electrical Engineering, 1996
- Engelska 8 s.
-
Serie: LiTH-ISY-R, 1400-3902 ; 1828
- Relaterad länk:
-
https://liu.diva-por... (primary) (Raw object)
-
visa fler...
-
https://urn.kb.se/re...
-
visa färre...
Abstract
Ämnesord
Stäng
- Two new reinforcement learning algorithms are presented. Both use a binary tree to store simple local models in the leaf nodes and coarser global models towards the root. It is demonstrated that a meaningful partitioning into local models can only be accomplished in a fused space consisting of both input and output. The first algorithm uses a batch like statistic procedure to estimate the reward functions in the fused space. The second one uses channel coding to represent the output- and input vectors allowing a simple iterative algorithm based on competing subsystems. The behaviors of both algorithms are illustrated in a preliminary experiment.
Nyckelord
- Learning algorithms
- Autonomous systems
- TECHNOLOGY
- TEKNIKVETENSKAP
Publikations- och innehållstyp
- vet (ämneskategori)
- rap (ämneskategori)