Exploring the Integration of Lisp into a Modern Reinforcement Learning Project Through the Use of Hy
Journal: International Journal of Advanced Trends in Computer Science and Engineering (IJATCSE) (Vol.11, No. 5)Publication Date: 2022-10-10
Authors : Kuo-pao Yang Max Cole Hayden Israel Madison Leblanc Noah Vernon;
Page : 186-190
Keywords : Hy; Lisp; NetHack; Reinforcement Learning;
Abstract
This paper explores the usage of Lisp in a small modern Reinforcement Learning (RL) project. The Lisp dialect, Hy programming language, is used to incorporate the traditional libraries and packages in up-to-date workflows. This project is centered around the usage of NetHack for RL. The MiniHack sandbox framework and NetHack Learning Environment (NLE) are used to create custom training/testing environments and tasks. The MiniHack sandbox framework creates a simple level editor and creation interface for use in the training and evaluation process of the agent. NLE is chosen as the working environment. For the agent model, this project adopts Torchbeast's PolyBeast, a PyTorch implementation of the IMPALA architecture. The usage of Hy within this project is forefront, and so it is implemented as much as possible to accomplish the tasks.
Other Latest Articles
- Desigualdad y estratificación socioeconómica en relación con el individualismo y el colectivismo cultural: una discusión teórica de su construcción desde la psicología social
- Experiencia de educación sensible en tres centros comerciales de Medellín; una experimentación con arte contemporáneo
- La cognición social en los padres de familia de los niños y adolescentes que presentan problemáticas de convivencia escolar
- Aprendizajes significativos en la formación de terapeutas familiares de la Universidad Católica Luis Amigó
- Panorama de las intervenciones psicológicas virtuales en Hispanoamérica y España antes de la pandemia COVID-19. Revisión documental
Last modified: 2022-10-11 00:27:50