Optimal Cooperation, Communication, and Learning in Decentralized Systems
Videos from BIRS Workshop
Vikram Krishnamurthy, University of British Columbia
Monday Oct 13, 2014 08:56 - 09:47
Social learning and active sensing
Tara Javidi, University of California San Diego
Monday Oct 13, 2014 09:48 - 10:19
Noisy Bayesian active learning
Tamer Basar, University of Illinois at Urbana Champaign
Monday Oct 13, 2014 10:41 - 11:33
Stochastic dynamic games and intricacy of information structures
Shlomo Zilberstein, University of Massachusetts Amherst
Tuesday Oct 14, 2014 08:32 - 09:18
Cooperative multi-agent planning in partially observable uncertain worlds
Matthijs Spaan, Delft University of Technology
Tuesday Oct 14, 2014 09:26 - 10:04
Multi-agent planning under uncertainty with communication
Frans Oliehoek, University of Amsterdam
Tuesday Oct 14, 2014 10:32 - 11:12
Exploiting structured representation in multi-agent sequential decision making
Mihailo Jovanovic, University of Minnesota
Tuesday Oct 14, 2014 11:12 - 12:02
Sparsity-promoting optimal control of distributed systems
Wing Shing Wong, Chinese University of Hong Kong
Tuesday Oct 14, 2014 13:35 - 14:11
Systems for open interaction
Rahul Jain, Univesity of Southern California
Tuesday Oct 14, 2014 14:11 - 14:50
The art of sequential optimization via simulations
Aditya Mahajan, McGill University
Tuesday Oct 14, 2014 14:51 - 15:31
The common information approach to decentralized stochastic control
Sanjay Lall, Stanford University
Tuesday Oct 14, 2014 16:01 - 16:43
Sufficient statistics for multi-agent decisions
Bahman Gharesifard, Queen's University
Tuesday Oct 14, 2014 17:29 - 18:06
On the convergence of strategic interaction dynamics on networks
Jason Marden, University of Colorado
Wednesday Oct 15, 2014 08:36 - 09:24
The role of information in multi-agent coordination
Gürdal Arslan, University of Hawaii
Wednesday Oct 15, 2014 09:25 - 10:04
Learning algorithms for stochastic dynamic games
David Leslie, Lancaster University
Wednesday Oct 15, 2014 10:04 - 10:35
Two-timescales game-theoretical learning with continuous action spaces
Johannes Hörner, Yale University
Wednesday Oct 15, 2014 11:03 - 11:41
Dynamic Bayesian games
Behrouz Touri, University of Colorado
Wednesday Oct 15, 2014 11:42 - 12:12
TS graph approach to evolutionary stability
Alex Olshevsky, University of Illinois at Urbana Champaign
Wednesday Oct 15, 2014 13:35 - 14:14
Linear time consensus
Shreyas Sundaram, University of Waterloo
Wednesday Oct 15, 2014 14:14 - 14:48
Spectral and structural properties of random graphs with applications to consensus dynamics on networks
Maxim Raginsky, University of Illinois, Urbana Champaign
Wednesday Oct 15, 2014 15:02 - 15:46
Online discrete optimization in social networks with inertia
András György, University of Alberta
Wednesday Oct 15, 2014 16:01 - 16:40
Online learning in Markov Decision Processes with changing reward sequences
Csaba Szepesvari, University of Alberta
Wednesday Oct 15, 2014 16:41 - 17:23
Online learning under delayed feedback
Vianney Perchet, Université Paris Diderot
Wednesday Oct 15, 2014 17:24 - 18:03
Blackwell approachability in (stochastic) games
Serdar Yüksel, Queen's University
Thursday Oct 16, 2014 08:33 - 09:20
Quantization for stabilization, optimization and approximation in networked control
Anant Sahai, University of California Berkeley
Thursday Oct 16, 2014 09:20 - 10:01
Information theory and decentralized control
Cedric Langbort, University of Illinois at Urbana-Champaign (UIUC)
Thursday Oct 16, 2014 10:03 - 10:47
On myopic strategies in dynamic adversarial team decision problems
Ohad Shamir, Weizmann Institute of Science
Thursday Oct 16, 2014 11:11 - 11:44
Information constraints in distributed and online learning
Vivek Borkar, Indian Institute of Technology Bombay
Thursday Oct 16, 2014 11:45 - 12:19
Gossip and related algorithms