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 proceedingConference contribution

40 Scopus citations

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 languageEnglish (US)
Title of host publicationIEEE International Conference on Intelligent Robots and Systems
Pages430-435
Number of pages6
StatePublished - Dec 26 2003
Externally publishedYes

Fingerprint

Dive into the research topics of 'A Robot that Reinforcement-Learns to Identify and Memorize Important Previous Observations'. Together they form a unique fingerprint.

Cite this