In many environments, only a relatively small subset of the complete state space is necessary in order to accomplish a given task. We develop a simple technique using emergency stops (e-stops) to exploit this phenomenon. Using e-stops significantly improves sample complexity by reducing the amount of required exploration, while retaining a performance bound that efficiently trades off the rate of convergence with a small asymptotic sub-optimality gap. We analyze the regret behavior of e-stops and present empirical results in discrete and continuous settings demonstrating that our reset mechanism can provide order-of-magnitude speedups on top of existing reinforcement learning methods.
Cite
@article{arxiv.1912.01649,
title = {Mo' States Mo' Problems: Emergency Stop Mechanisms from Observation},
author = {Samuel Ainsworth and Matt Barnes and Siddhartha Srinivasa},
journal= {arXiv preprint arXiv:1912.01649},
year = {2019}
}