AI Chat AI Image Generator AI Video Text to Speech

Mo' States Mo' Problems: Emergency Stop Mechanisms from Observation

12/03/2019

∙

by Samuel Ainsworth, et al.

∙

∙

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.

Samuel Ainsworth
4 publications
Matt Barnes
12 publications
Siddhartha Srinivasa
29 publications

research

∙ 11/13/2019

Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning

We present an algorithm, HOMER, for exploration and reinforcement learni...

15 Dipendra Misra, et al. ∙

research

∙ 11/20/2019

Bayesian Curiosity for Efficient Exploration in Reinforcement Learning

Balancing exploration and exploitation is a fundamental part of reinforc...

0 Tom Blau, et al. ∙

research

∙ 11/30/2022

Efficient Reinforcement Learning (ERL): Targeted Exploration Through Action Saturation

Reinforcement Learning (RL) generally suffers from poor sample complexit...

0 Loris Di Natale, et al. ∙

research

∙ 03/07/2021

The Effect of Q-function Reuse on the Total Regret of Tabular, Model-Free, Reinforcement Learning

Some reinforcement learning methods suffer from high sample complexity c...

0 Volodymyr Tkachuk, et al. ∙

research

∙ 10/15/2020

Optimal Dispatch in Emergency Service System via Reinforcement Learning

In the United States, medical responses by fire departments over the las...

0 Cheng Hua, et al. ∙

research

∙ 05/25/2023

Sample Efficient Reinforcement Learning in Mixed Systems through Augmented Samples and Its Applications to Queueing Networks

This paper considers a class of reinforcement learning problems, which i...

0 Honghao Wei, et al. ∙

research

∙ 01/01/2022

Transfer RL across Observation Feature Spaces via Model-Based Regularization

In many reinforcement learning (RL) applications, the observation space ...

9 Yanchao Sun, et al. ∙