@article{Bacon_Precup_2018, title={Constructing Temporal Abstractions Autonomously in Reinforcement Learning}, volume={39}, url={https://ojs.aaai.org/aimagazine/index.php/aimagazine/article/view/2780}, DOI={10.1609/aimag.v39i1.2780}, abstractNote={The idea of temporal abstraction, i.e. learning, planning and representing the world at multiple time scales, has been a constant thread in AI research, spanning sub-fields from classical planning and search to control and reinforcement learning. For example, programming a robot typically involves making decisions over a set of controllers, rather than working at the level of motor torques. While temporal abstraction is a very natural concept, learning such abstractions with no human input has proved quite daunting. In this paper, we present a general architecture, called option-critic, which allows learning temporal abstractions automatically, end-to-end, simply from the agent’s experience. This approach allows continual learning and provides interesting qualitative and quantitative results in several tasks.}, number={1}, journal={AI Magazine}, author={Bacon, Pierre-Luc and Precup, Doina}, year={2018}, month={Mar.}, pages={39-50} }