Bandits and Agents: How to Incentivize Exploration?

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=lKN7eb1u6wQ


Duration: 39:07
650 views
6

Aleksandrs Slivkins, Microsoft Research
https://simons.berkeley.edu/talks/aleksandrs-slivkins-09-22-2016
Optimization and Decision-Making Under Uncertainty



Other Videos By Simons Institute for the Theory of Computing


2016-10-04Unifying Logic and Probability: The BLOG Language
2016-09-27Number-Theoretic Methods in Quantum Computing
2016-09-27Algorithm Design in the Modern Era: Dealing with Uncertainty and Incentives
2016-09-23Optimal Online Algorithms via Linear Scaling
2016-09-23Secretary Problems and Online Selection with A Priori Information
2016-09-23Scheduling with Uncertain Processing Times
2016-09-23Online Algorithms with Recourse
2016-09-23Online Flow-Time Optimization
2016-09-23Competitive Algorithms from Competitive Equilibria
2016-09-22Online Ad Allocation: Robust Optimization for Repeated Auctions
2016-09-22Bandits and Agents: How to Incentivize Exploration?
2016-09-22A Unified Duality Theory for Bayesian Mechanism Design
2016-09-22Simple Pricing Schemes for Consumers with Evolving Values
2016-09-22Procrastination with Variable Present Bias
2016-09-22Avoiding Cascading Failures for Time-of-Use Pricing
2016-09-21Online Optimization and Learning Under Long-Term Convex Constraints and Objectives
2016-09-21Learning in Games with Best-Response Oracles
2016-09-21Distribution-Free Models of Social and Information Networks
2016-09-21Revisiting the Exploration-Exploitation Trade-Off in Bandit Models
2016-09-21Always Valid Inference: Continuous Monitoring of A/B Tests
2016-09-21Kernel-Based Methods for Bandit Convex Optimization


Tags:
Simons Institute
Theory of Computing
Theory of Computation
Theoretical Computer Science
Computer Science
UC Berkeley
Optimization and Decision-Making Under Uncertainty
Aleksandrs Slivkins