A Robot that Reinforcement-Learns to Identify and Memorize Important Previous Observations

Bram Bakker; Viktor Zhumatiy; Gabriel Gruener; Jürgen Schmidhuber

A Robot that Reinforcement-Learns to Identify and Memorize Important Previous Observations

Bram Bakker, Viktor Zhumatiy, Gabriel Gruener, Jürgen Schmidhuber

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

It is difficult to apply traditional reinforcement learning algorithms to robots, due to problems with large and continuous domains, partial observability, and limited numbers of learning experiences. This paper deals with these problems by combining: 1. reinforcement learning with memory, implemented using an LSTM recurrent neural network whose inputs are discrete events extracted from raw inputs; 2. online exploration and offline policy learning. An experiment with a real robot demonstrates the methodology's feasibility.

Original language	English (US)
Title of host publication	IEEE International Conference on Intelligent Robots and Systems
Pages	430-435
Number of pages	6
State	Published - Dec 26 2003
Externally published	Yes

Cite this

@inproceedings{e1d0407ae6d44d42aeba00ad89685f8b,

title = "A Robot that Reinforcement-Learns to Identify and Memorize Important Previous Observations",

abstract = "It is difficult to apply traditional reinforcement learning algorithms to robots, due to problems with large and continuous domains, partial observability, and limited numbers of learning experiences. This paper deals with these problems by combining: 1. reinforcement learning with memory, implemented using an LSTM recurrent neural network whose inputs are discrete events extracted from raw inputs; 2. online exploration and offline policy learning. An experiment with a real robot demonstrates the methodology's feasibility.",

author = "Bram Bakker and Viktor Zhumatiy and Gabriel Gruener and J{\"u}rgen Schmidhuber",

note = "Generated from Scopus record by KAUST IRTS on 2022-09-14",

year = "2003",

month = dec,

day = "26",

language = "English (US)",

pages = "430--435",

booktitle = "IEEE International Conference on Intelligent Robots and Systems",

}

TY - GEN

T1 - A Robot that Reinforcement-Learns to Identify and Memorize Important Previous Observations

AU - Bakker, Bram

AU - Zhumatiy, Viktor

AU - Gruener, Gabriel

AU - Schmidhuber, Jürgen

N1 - Generated from Scopus record by KAUST IRTS on 2022-09-14

PY - 2003/12/26

Y1 - 2003/12/26

N2 - It is difficult to apply traditional reinforcement learning algorithms to robots, due to problems with large and continuous domains, partial observability, and limited numbers of learning experiences. This paper deals with these problems by combining: 1. reinforcement learning with memory, implemented using an LSTM recurrent neural network whose inputs are discrete events extracted from raw inputs; 2. online exploration and offline policy learning. An experiment with a real robot demonstrates the methodology's feasibility.

AB - It is difficult to apply traditional reinforcement learning algorithms to robots, due to problems with large and continuous domains, partial observability, and limited numbers of learning experiences. This paper deals with these problems by combining: 1. reinforcement learning with memory, implemented using an LSTM recurrent neural network whose inputs are discrete events extracted from raw inputs; 2. online exploration and offline policy learning. An experiment with a real robot demonstrates the methodology's feasibility.

UR - http://www.scopus.com/inward/record.url?scp=0346149797&partnerID=8YFLogxK

M3 - Conference contribution

SP - 430

EP - 435

BT - IEEE International Conference on Intelligent Robots and Systems

ER -

A Robot that Reinforcement-Learns to Identify and Memorize Important Previous Observations

Abstract

Other files and links

Fingerprint

Cite this