December
2019
Mo'States Mo'Problems: Emergency Stop Mechanisms from Observation
Authors:
Abstract:
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.
copied = false, 2000);
">
@conference{Ainsworth-2019-122659,
author = {Samuel Ainsworth And Matt Barnes And Siddhartha Srinivasa},
title = {Mo'States Mo'Problems: Emergency Stop Mechanisms from Observation},
booktitle = {Proceedings of (NeurIPS) Neural Information Processing Systems},
year = {2019},
month = {December},
pages = {15156 - 15166},
}
author = {Samuel Ainsworth And Matt Barnes And Siddhartha Srinivasa},
title = {Mo'States Mo'Problems: Emergency Stop Mechanisms from Observation},
booktitle = {Proceedings of (NeurIPS) Neural Information Processing Systems},
year = {2019},
month = {December},
pages = {15156 - 15166},
}