Talks and Presentations

• Approximate planning and learning for partially observed systems (slides) (video)
  University of Texas, A&M, Oct 2022
• Reinforcement Learning in Stationary Mean-Field Games (slides) (video)
  Machine Learning and Mean-Field Games, Nov 2021
• Robustness and sample complexity of model-based MARL for general-sum Markov games (slides)
  Workshop on Agent behavior in combinatorial game theory, Nov 2021
• Learning to control network-coupled subsystems with unknown dynamics (slides) (video)
  Workshop on Mean-field games on Networks, Nov 2021
• Approximate planning and learning for partially observed systems (slides) (video)
  Reinforcement learning and sotchastic control in queues and networks (ReStoq) Workshop, WiOpt, Oct 2021
• Approximate planning and learning for partially observed systems (slides) (video)
  Communication and Signal Processing Seminar, University of Michigan, Feb 2020
• Approximate planning and learning for partially observed systems (slides)
  Mila RL Reading Group, Feb 2020
• Information state (and its approximations) for stochastic control (slides)
  BIRS-CMO Workshop on Multi-Stage Stochastic Optimization for Clean Energy Transition, Sep 2019
• Decentralized Kalman Filtering (slides)
  Fields Workshop on Stochastic Processes and their Applications, Ottawa, Aug 2017
• Mean-field teams
  Systems Science Seminar, University of Michigan, July 2017
• Fundamental limits of remote estimation (slides)
  BLISS Seminar, UC Berkeley, Mar 2017
• Remote state estimation over erasure channels: structure of optimal strategies and fundamental limits (slides)
  IT Forum, Stanford, Nov 2016
• Optimal decentralized control of systems with partially exchangeable agents (slides)
  Allerton Conference on Communication, Control, and Computing, Sep 2016
• Fundamental limits of remote estimation under communication constraints (slides)
  Modeling and Optimization in Mobile, Ad-Hoc Wireless Networks (WiOpt), May 2016
• Remote estimation of Markov processes under communication constraints (slides)
  Applied Probability Conference, Rutgers, Oct 2015
• Mean-field teams
  CommNets Seminar, USC, Aug 2015
• Fundamental limits of remote-estimation under communication constraints (slides)
  Mathematical Cybernetics: Hybrid, Stochastic and Decentralized Systems, May 2015
• Optimal real-time transmission of Markov sources under constraints on the number of transmissions (slides)
  University of Toronto, Nov 2014
• Decentralized stochastic control: The person-by-person and common information approaches (slides) (video)
  BIRS Workshop on Optimal Cooperation, Communication, and Learning in Decentralized Systems, Banff, Oct 2014
• Decentralized stochastic control (slides)
  REPARTI (Regroupement pour l'étude des environnements partagés intelligents répartis) Workshop, Quebec City, May 2014
• Dynamic Programming in Decentralized Stochastic Control
  GERAD (Group d'Etudes et de Recherche en Analyse des Décisions) Seminar, Montreal, October 2012
• Optimal decentralized stochastic control: A common information approach (slides)
  Concordia University, Montreal, October 2012
  GERAD (Group d'Etudes et de Recherche en Analyse des Décisions) Seminar, Montreal, April 2012
• Optimal decentralized stochastic control: The designer and common information approaches
  CEA-EDF-INRIA Summer School on Stochastic Optimization, Cadarache, July 2012
• An overview of structural results in real-time communication (slides)
  BIRS workshop on interactive information theory, Banff, January 2012
• Separation results for decentralized stochastic control under delayed sharing of information (slides)
  Queen's University, Kingston, July 2011
• Introduction to sequential teams (slides)
  MITACS workshop on fusion and inference in networks, Bellairs Insitute, Barbados, March 2011
• Decentralized decision making under uncertainty (slides)
  Ecole des Pont, Paris, June 2010
  McGill University, Montreal, May 2010
• Auxiliary random variables in multi-terminal communication with feedback: a decentralized control perspective
  University of California, Berkeley, April 2010
  Stanford University, Stanford, April 2010
• Interconnections between information theory and decentralized stochastic control
  University of Illinois, Urbana Champaign, March 2010
• Structure of optimal decentralized control policies: an axiomatic approach (slides)
  University of Notre Dame, South Bend, March 2010
• Role of information structures in decentralized decision making (slides)
  University of California, Los Angeles, Feb 2010
• Graphical reasoning for decentralized systems (slides)
  University of Michigan, Ann Arbor, Oct 2009
• Optimal design of sequential teams (slides)
  Queen's University, Kingston, May 2009
  McGill University, Montreal, May 2009