Наредни састанак Семинара биће одржан у петак, 29. септембра 2023, у сали 301ф Матматичког института САНУ са почетком у 12.30.
Предавач: Драган Стевановић, Математички институт САНУ
Наслов предавања: REINFORCEMENT LEARNING FOR GRAPH THEORY – CROSS-ENTROPY METHOD AND BASIC GRAPH ENVIRONMENTS
Апстракт: Adam Zsolt Wagner [arXiv:2104.14516] recently showed how reinforcement learning can be applied to construct (counter)examples in graph theory. We will showcase here a more readable, more stable and significantly faster reimplementation of his approach. We further implement several new reinforcement learning environments that cover constructions of simple graphs and trees, their signed variants, and graph with bounded maximum vertex degree. The presented concepts are illustrated by constructing counterexamples for several conjectures from literature
Напомена: Предавања се могу пратити на даљину преко линка:
https://miteam.mi.sanu.ac.rs/call/T9XDGChhq8aDcNqmz/qw7wIwci2jv2rdg9I9CrXkm7OJhF_LB8DfjXZp4jTFV
Регистрациона форма је доступна на:
https://miteam.mi.sanu.ac.rs/asset/tz97w4Hu4c3unsJ7N