Online Combinatorial Optimization under Bandit Feedback
Multi-Armed Bandits (MAB) constitute the most fundamental model for sequential decision making problems with an exploration vs. exploitation trade-off. In such problems, the decision maker selects an arm in each round and observes a realization of the corresponding unknown reward distribution. Each...
| Main Author: | |
|---|---|
| Format: | Others |
| Language: | English |
| Published: |
KTH, Reglerteknik
2016
|
| Subjects: | |
| Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-181321 http://nbn-resolving.de/urn:isbn:978-91-7595-836-1 |