BEGIN:VCALENDAR
VERSION:2.0
X-WR-CALNAME;VALUE=TEXT:Automated Market Design via Reinforcement Learning
PRODID:-//Harvard events data//EN
BEGIN:VEVENT
UID:event_1635609_0
SUMMARY:Automated Market Design via Reinforcement Learning
DESCRIPTION:<p>	<strong>Speaker:</strong>  Gianluca Brero<br><br><strong>Title:</strong><span><span>  Automated Market Design via Reinforcement Learning</span></span></p><span><span><strong>Abstract:</strong>  In this talk, I will introduce the use of reinforcement learning to design algorithmic markets. First, I will show how (deep) reinforcement learning algorithms can be used to design sequential price mechanisms, where we can assume truthful agents’ behavior. I will then consider the more general class of mechanisms that combine a messaging round with a sequential-pricing stage. The rules of the sequential-pricing stage—and in particular the way these rules use messages—determine the way the messaging stage is used. This is a Stackelberg game where the designer is the leader and fixes the mechanism rules, inducing an equilibrium amongst agents (the followers). I will introduce a novel single-agent Stackelberg MDP formulation, where the leader learns to effect a follower equilibrium that optimizes its objective. In the last part of my talk, I will show how the Stackelberg MDP framework can be used to design economic platforms that prevent collusive behaviors of AI pricing algorithms.</span></span>
LOCATION:SEC 1.413 & on Zoom here:  https://harvard.zoom.us/j/97692964231?pwd=K05BMEhDNTZtbUhHYkZ5S21qZ2FKQT09#success
STATUS:CONFIRMED
DTSTART:20220401T170000Z
DTEND:20220401T183000Z
END:VEVENT
END:VCALENDAR