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%3A00223236" target="_blank" >RIV/68407700:21230/14:00223236 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Safe Exploration Techniques for Reinforcement Learning - An Overview

Popis výsledku v původním jazyce

We overview diferent approaches to safety in (semi)autonomous robotics. Particularly, we focus on how to achieve safe behavior of a robot if it is requested to perform exploration of unknown states. Presented methods are studied from the viewpoint of reinforcement learning, a partially-supervised machine learning method. Recently, it has shown to be one of the most suitable learning methods in robotics. However, to collect training data for this algorithm, the robot is required to freely explore the state space ? which can lead to possibly dangerous situations. The role of safe exploration is to provide a framework allowing exploration while preserving safety. The examined methods range from simple algorithms which utilize precise physical models to sophisticated methods based on previous experience or state prediction. Our overview also addresses the issues of how to define safety in the real-world applications. It is apparent that absolute safety is unachievable in the continuous and

Název v anglickém jazyce

Safe Exploration Techniques for Reinforcement Learning - An Overview

Popis výsledku anglicky

We overview diferent approaches to safety in (semi)autonomous robotics. Particularly, we focus on how to achieve safe behavior of a robot if it is requested to perform exploration of unknown states. Presented methods are studied from the viewpoint of reinforcement learning, a partially-supervised machine learning method. Recently, it has shown to be one of the most suitable learning methods in robotics. However, to collect training data for this algorithm, the robot is required to freely explore the state space ? which can lead to possibly dangerous situations. The role of safe exploration is to provide a framework allowing exploration while preserving safety. The examined methods range from simple algorithms which utilize precise physical models to sophisticated methods based on previous experience or state prediction. Our overview also addresses the issues of how to define safety in the real-world applications. It is apparent that absolute safety is unachievable in the continuous and

Druh

V_souhrn - Souhrnná výzkumná zpráva

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

Počet stran výsledku

10

Místo vydání

Praha

Název nakladatele resp. objednatele

Center for Machine Perception, K13133 FEE Czech Technical University

Verze

—