Workshops

Spring 2022

Multi-Agent Reinforcement Learning and Bandit Learning

May 2, 2022 to May 5, 2022

Return to event »

Monday, May 2nd, 2022
8:30 am–9:00 am		Coffee and Check-In
9:00 am–9:05 am		Opening Remarks
9:05 am–9:45 am		"Calibeating": Beating Forecasters at Their Own Game Sergiu Hart (Hebrew University of Jerusalem)
9:45 am–10:15 am		Break
10:15 am–11:00 am		V-Learning: Simple, Efficient, Decentralized Algorithm for Multiagent RL Chi Jin (Princeton University)
11:00 am–11:30 am		Break
11:30 am–12:15 pm		What is the Statistical Complexity of Reinforcement Learning? Sham Kakade (Harvard and MSR)
12:15 pm–2:00 pm		Lunch
2:00 pm–2:30 pm		No-Regret Learning in Time-Varying Zero-Sum Games Haipeng Luo (University of Southern California)
2:30 pm–3:00 pm		Policy Gradients in General-Sum Dynamic Games: When Do They Even Converge? Eric Mazumdar (Caltech)
3:00 pm–3:15 pm		Break
3:15 pm–4:00 pm		The Complexity of Infinite-Horizon General-Sum Stochastic Games: Turn-Based and Simultaneous Play Vidya Muthukumar (Georgia Institute of Technology)
4:00 pm–5:00 pm		Reception

Tuesday, May 3rd, 2022
8:30 am–9:00 am		Coffee and Check-In
9:00 am–9:45 am		The Complexity of Markov Equilibrium in Stochastic Games Noah Golowich (MIT)
9:45 am–10:15 am		Break
10:15 am–11:00 am		A Regret Minimization Approach to Mutli-Agent Control and RL Elad Hazan (Princeton University and Google Research)
11:00 am–11:30 am		Break
11:30 am–12:15 pm		Multi-Agent Reinforcement Learning in the High Population Regime Tamer Başar (University of Illinois Urbana-Champaign)
12:15 pm–2:00 pm		Lunch
2:00 pm–2:30 pm		Learning Automata as Building Blocks for MARL Ann Nowe (Vrije Universiteit Brussel)
2:30 pm–3:00 pm		On Rewards in Multi-Agent Systems Doina Precup (McGill University / DeepMind Montreal)
3:00 pm–3:30 pm		Break
3:30 pm–4:00 pm		Independent Learning in Stochastic Games Kaiqing Zhang (MIT)
4:00 pm–4:30 pm		Sequential Information Design: Markov Persuasion Process and Its Efficient Reinforcement Learning Zhuoran Yang (UC Berkeley)
4:30 pm–5:30 pm		Open Problem Session

Wednesday, May 4th, 2022
8:30 am–9:00 am		Coffee and Check-In
9:00 am–9:45 am		Multi-Agent Reinforcement Learning Towards Zero-Shot Communication Kalesha Bullard (DeepMind)
9:45 am–10:15 am		Break
10:15 am–11:00 am		Kernelized Multiplicative Weights for 0/1-Polyhedral Games: Bridging the Gap Between Learning in Extensive-Form and Normal-Form Games Gabriele Farina (Carnegie Mellon University)
11:00 am–11:30 am		Break
11:30 am–12:00 pm		General Game-Theoretic Multiagent Reinforcement Learning Marc Lanctot (DeepMind)
12:00 pm–2:00 pm		Lunch
2:00 pm–2:30 pm		When Is Offline Two-Player Zero-Sum Markov Game Solvable? Simon Du (University of Washington)
2:30 pm–3:00 pm		Variants and Invariants in No-Regret Algorithms Sylvain Sorin (Sorbonne Universite)
3:00 pm–3:30 pm		Break
3:30 pm–4:00 pm		What Does Machine Learning Offer Game Theory (And Vice Versa)? Alex Peysakhovich (Meta AI)
4:00 pm–4:30 pm		Multi-Player Bandits With No Collisions Mark Sellke (Stanford)

Thursday, May 5th, 2022
8:30 am–9:00 am		Coffee and Check-In
9:00 am–9:45 am		Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games Ioannis Panageas (UC Irvine)
9:45 am–10:15 am		Break
10:15 am–11:00 am		Learning and Equilibrium Refinements Drew Fudenberg (MIT)
11:00 am–11:30 am		Break
11:30 am–12:15 pm		No-Regret Learning in Extensive-Form Games Amy Greenwald (Brown University)
12:15 pm–2:00 pm		Lunch
2:00 pm–2:30 pm		Learning Decentralized Policies in Multiagent Systems: How to Learn Efficiently and What Are the Learned Policies? Na Li (Harvard University)
2:30 pm–2:45 pm		Break
2:45 pm–3:30 pm		The Role of Conventions in Adaptive Human-AI Interaction Dorsa Sadigh (Stanford University)