Doorkeeper

Introduction to reinforcement learning :Talk by Akinori Tanaka : AIP math-sci team's seminar

Mon, 06 Aug 2018 13:00 - 14:30 JST

Keio Univ. Yagami-campus, Building 14, Room 631A

3-14-1 Kouhoku-ku, Hiyoshi, Yokohama 223-8522, JAPAN

Register

Registration is closed

Get invited to future events

Free admission

Description

abstract:
I'd like to briefly review mathematical basics of reinforcement learning including the setup, the Markov Decision Process, and three training schemes, value-based algorithm, policy-based algorithm, and hybrid of them so-called actor-critic algorithm.

About this community

RIKEN AIP Public

RIKEN AIP Public

Public events of RIKEN Center for Advanced Intelligence Project (AIP)

Join community