Unifying Task Specification in Reinforcement Learning
- Martha White, University of Alberta
Reinforcement learning tasks are typically specified as Markov decision processes. This formalism has been highly successful, though specifications often couple the dynamics of the environment and the learning objective. This lack of modularity can complicate generalization of the task specification, as well as obfuscate connections between different task settings, such as episodic and continuing. In this work, we introduce the RL task formalism, that provides a unification through simple constructs including a generalization to transition-based discounting. Through a series of examples, we demonstrate the generality and utility of this formalism. Finally, we extend standard learning constructs, including Bellman operators, and extend some seminal theoretical results, including approximation errors bounds. Overall, we provide a well-understood and sound formalism on which to build theoretical results and simplify algorithm use and development.
Citation
M. White. "Unifying Task Specification in Reinforcement Learning". International Conference on Machine Learning (ICML), (ed: Doina Precup, Yee Whye Teh), pp 3742-3750, August 2017.| Keywords: | |
| Category: | In Conference |
| Web Links: | PMLR |
BibTeX
@incollection{White:ICML17,
author = {Martha White},
title = {Unifying Task Specification in Reinforcement Learning},
Editor = {Doina Precup, Yee Whye Teh},
Pages = {3742-3750},
booktitle = {International Conference on Machine Learning (ICML)},
year = 2017,
}Last Updated: February 25, 2020Submitted by Sabina P
