Kaixhin/Atari

Implement optimality tightening

Open

#60 aberto em 11 de dez. de 2016

Ver no GitHub
 (8 comments) (0 reactions) (0 assignees)Lua (72 forks)github user discovery
enhancementhelp wanted

Métricas do repositório

Stars
 (263 stars)
Métricas de merge de PR
 (Nenhuma PRs mesclada em 30d)

Description

Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening potentially speeds up Q-learning by an order of magnitude! Apparently not too hard to implement either.

Guia do colaborador