EasyRL: A Simple and Extensible Reinforcement Learning Framework

Authors

  • Neil Hulbert University of Washington Tacoma
  • Sam Spillers University of Washington Tacoma
  • Brandon Francis University of Washington Tacoma
  • James Haines-Temons University of Washington Tacoma
  • Ken Gil Romero University of Washington Tacoma
  • Benjamin De Jager University of Washington Tacoma
  • Sam Wong University of Washington Tacoma
  • Kevin Flora University of Washington Tacoma
  • Bowei Huang University of Washington Tacoma
  • Athirai A. Irissappane University of Washington Tacoma

Keywords:

RL Framework, Deep Reinforcement Learning

Abstract

In recent years, Reinforcement Learning (RL), has become a popular field of study as well as a tool for enterprises working on cutting-edge artificial intelligence research. To this end, many researchers have built RL frameworks such as openAI Gym, and KerasRL for ease of use. While these works have made great strides towards bringing down the barrier of entry for those new to RL, we propose a much simpler framework called EasyRL, by providing an interactive graphical user interface for users to train and evaluate RL agents. As it is entirely graphical, EasyRL does not require programming knowledge for training and testing simple built-in RL agents. EasyRL also supports custom RL agents and environments, which can be highly beneficial for RL researchers in evaluating and comparing their RL models.

Downloads

Published

2021-05-18

How to Cite

Hulbert, N., Spillers, S., Francis, B., Haines-Temons, J., Gil Romero, K., De Jager, B., Wong, S., Flora, K., Huang, B., & A. Irissappane, A. (2021). EasyRL: A Simple and Extensible Reinforcement Learning Framework. Proceedings of the AAAI Conference on Artificial Intelligence, 35(18), 16041-16043. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/18006