Deep Reinforcement Learning With Macro-Actions
Machine Learning
2016-06-16 v1 Artificial Intelligence
Neural and Evolutionary Computing
Abstract
Deep reinforcement learning has been shown to be a powerful framework for learning policies from complex high-dimensional sensory inputs to actions in complex tasks, such as the Atari domain. In this paper, we explore output representation modeling in the form of temporal abstraction to improve convergence and reliability of deep reinforcement learning approaches. We concentrate on macro-actions, and evaluate these on different Atari 2600 games, where we show that they yield significant improvements in learning speed. Additionally, we show that they can even achieve better scores than DQN. We offer analysis and explanation for both convergence and final results, revealing a problem deep RL approaches have with sparse reward signals.
Cite
@article{arxiv.1606.04615,
title = {Deep Reinforcement Learning With Macro-Actions},
author = {Ishan P. Durugkar and Clemens Rosenbaum and Stefan Dernbach and Sridhar Mahadevan},
journal= {arXiv preprint arXiv:1606.04615},
year = {2016}
}