New Methods for Learning from Heterogeneous and Strategic Agents
1 Introduction In this doctoral thesis, we address several representative problems that arise in the context of learning from multiple heterogeneous agents. These problems are relevant to many modern applications such as crowdsourcing and internet advertising. In scenarios such as crowdsourcing, th...
Main Author: | Divya, Padmanabhan |
---|---|
Other Authors: | Shevade, Shirish |
Language: | en_US |
Published: |
2018
|
Subjects: | |
Online Access: | http://etd.iisc.ernet.in/2005/3562 http://etd.iisc.ernet.in/abstracts/4430/G28407-Abs.pdf |
Similar Items
-
Learning the Truth by Weakly Connected Agents in Social Networks Using Multi-Armed Bandit
by: Olusola Tolulope Odeyomi
Published: (2020-01-01) -
Structured Stochastic Bandits
by: Magureanu, Stefan
Published: (2016) -
Multi-Armed Bandits for Spectrum Allocation in Multi-Agent Channel Bonding WLANs
by: Sergio Barrachina-Munoz, et al.
Published: (2021-01-01) -
Optimal Finite Horizon Sensing for Wirelessly Powered Devices
by: Mehdi Salehi Heydar Abad, et al.
Published: (2019-01-01) -
A Study of Thompson Sampling Approach for the Sleeping Multi-Armed Bandit Problem
by: Chatterjee, Aritra
Published: (2018)