Minimizing Regret in Combinatorial Bandits and Reinforcement Learning

Minimizing Regret in Combinatorial Bandits and Reinforcement Learning

This thesis investigates sequential decision making tasks that fall in the framework of reinforcement learning (RL). These tasks involve a decision maker repeatedly interacting with an environment modeled by an unknown finite Markov decision process (MDP), who wishes to maximize a notion of reward a...

Full description

Bibliographic Details
Main Author: Talebi Mazraeh Shahi, Mohammad Sadegh
Format: Doctoral Thesis
Language:English
Published: KTH, Reglerteknik 2017
Subjects:
Multi-armed Bandits
Reinforcement Learning
Regret Minimization
Statistics
Engineering and Technology
Teknik och teknologier
Online Access:http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-219970
http://nbn-resolving.de/urn:isbn:978-91-7729-618-8

Internet

http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-219970
http://nbn-resolving.de/urn:isbn:978-91-7729-618-8

Similar Items