Safe Exploration Techniques for Reinforcement Learning - An Overview

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F14%3A00223262" target="_blank" >RIV/68407700:21230/14:00223262 - isvavai.cz</a>

Výsledek na webu

<a href="http://cmp.felk.cvut.cz/~peckama2/papers/safe_exploration_overview_lncs.pdf" target="_blank" >http://cmp.felk.cvut.cz/~peckama2/papers/safe_exploration_overview_lncs.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-13823-7" target="_blank" >10.1007/978-3-319-13823-7</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Safe Exploration Techniques for Reinforcement Learning - An Overview

Popis výsledku v původním jazyce

We overview different approaches to safety in (semi)autonomous robotics. Part icularly, we focus on how to achieve safe behavior of a robot if it is requested to perform ex ploration of unknown states. Presented methods are studied from the viewpoint ofreinforcement learning, a partially-supervised machine learning method. To collect training data for this a lgorithm, the robot is required to freely explore the state space - which can lead to possibly dangerous situations. The role of safe explorationis to provide a framework allowing explora tion while preserving safety. The examined methods range from simple algorithms to sophisticat ed methods based on previous experience or state prediction. Our overview also addresses the i ssues of how to define safety in the real-world applications (apparently absolute safety is un achievable in the continuous and random real world). In the conclusion we also suggest several ways that are worth researching more thoroughly.

Název v anglickém jazyce

Safe Exploration Techniques for Reinforcement Learning - An Overview

Popis výsledku anglicky

We overview different approaches to safety in (semi)autonomous robotics. Part icularly, we focus on how to achieve safe behavior of a robot if it is requested to perform ex ploration of unknown states. Presented methods are studied from the viewpoint ofreinforcement learning, a partially-supervised machine learning method. To collect training data for this a lgorithm, the robot is required to freely explore the state space - which can lead to possibly dangerous situations. The role of safe explorationis to provide a framework allowing explora tion while preserving safety. The examined methods range from simple algorithms to sophisticat ed methods based on previous experience or state prediction. Our overview also addresses the i ssues of how to define safety in the real-world applications (apparently absolute safety is un achievable in the continuous and random real world). In the conclusion we also suggest several ways that are worth researching more thoroughly.

Druh

D - Stať ve sborníku

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2014

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Modelling and Simulation for Autonomous Systems

ISBN

978-3-319-13822-0

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

19

Strana od-do

357-375

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Rome

Datum konání akce

5. 5. 2014

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—