Reactive reinforcement learning in asynchronous environments
- Jaden B. Travnik
- Kory Wallace Mathewson
- Richard S. Sutton, Department of Computing Science, University of Alberta
- Patrick M. Pilarski
The relationship between a reinforcement learning (RL) agent and an asynchronous environment is often ignored. Frequently used models of the interaction between an agent and its environment, such as Markov Decision Processes (MDP) or Semi-Markov Decision Processes (SMDP), do not capture the fact that, in an asynchronous environment, the state of the environment may change during computation performed by the agent. In an asynchronous environment, minimizing reaction time—the time it takes for an agent to react to an observation—also minimizes the time in which the state of the environment may change following observation. In many environments, the reaction time of an agent directly impacts task performance by permitting the environment to transition into either an undesirable terminal state or a state where performing the chosen action is inappropriate. We propose a class of reactive reinforcement learning algorithms that address this problem of asynchronous environments by immediately acting after observing new state information. We compare a reactive SARSA learning algorithm with the conventional SARSA learning algorithm on two asynchronous robotic tasks (emergency stopping and impact prevention), and show that the reactive RL algorithm reduces the reaction time of the agent by approximately the duration of the algorithm's learning update. This new class of reactive algorithms may facilitate safer control and faster decision making without any change to standard learning guarantees.
Citation
J. Travnik, K. Mathewson, R. Sutton, P. Pilarski. "Reactive reinforcement learning in asynchronous environments". Frontiers in Robotics and AI, 5, pp n/a, June 2018.| Keywords: | |
| Category: | In Journal |
| Web Links: | Journal |
| DOI |
BibTeX
@article{Travnik+al:18,
author = {Jaden B. Travnik and Kory Wallace Mathewson and Richard S. Sutton
and Patrick M. Pilarski},
title = {Reactive reinforcement learning in asynchronous environments},
Volume = "5",
Pages = {n/a},
journal = {Frontiers in Robotics and AI},
year = 2018,
}Last Updated: November 10, 2020Submitted by Sabina P
