Active Reinforcement Learning: Observing Rewards at a Cost
Machine Learning
2020-11-26 v2 Artificial Intelligence
Machine Learning
Abstract
Active reinforcement learning (ARL) is a variant on reinforcement learning where the agent does not observe the reward unless it chooses to pay a query cost c > 0. The central question of ARL is how to quantify the long-term value of reward information. Even in multi-armed bandits, computing the value of this information is intractable and we have to rely on heuristics. We propose and evaluate several heuristic approaches for ARL in multi-armed bandits and (tabular) Markov decision processes, and discuss and illustrate some challenging aspects of the ARL problem.
Cite
@article{arxiv.2011.06709,
title = {Active Reinforcement Learning: Observing Rewards at a Cost},
author = {David Krueger and Jan Leike and Owain Evans and John Salvatier},
journal= {arXiv preprint arXiv:2011.06709},
year = {2020}
}
Comments
Originally appeared at the NeurIPS 2016 "Future of Interactive Learning Machines (FILM)" workshop