BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//OneJoy//events//EN
BEGIN:VEVENT
UID:onejoy-event-58072@onejoy
DTSTAMP:20261005T081456Z
DTSTART:20261006T003000Z
DTEND:20261006T023000Z
SUMMARY:MARL: Population Training with Exact PSRO
LOCATION:
DESCRIPTION:Last meeting (https://youtu.be/Tt-8F6rcHEo) we revisited the population training algorithm introduced in Chapter 9 of Multi-Agent Reinforcement Learning: Foundations and Modern Approaches (https://www.marl-book.com/) and considered only tabular problems with exact solution techniques. That version of the algorithm has some limitations regarding the ability to learn stochastic equilibrium solutions which is often required in stochastic games with simultaneous actions.\n\nIn this meeting we will exp\nhttps://onejoy.io/event/58072
URL:https://onejoy.io/event/58072
END:VEVENT
END:VCALENDAR