Measuring the effectiveness of reinforcement learning for behavior-based robots

John Shackleton, Maria Gini

Research output: Contribution to journalArticlepeer-review

5 Scopus citations

Abstract

We explore the use of behavior-based architectures within the context of reinforcement learning and examine the effects of using different behavior-based architectures on the ability to learn correctly and efficiently the task at hand. In particular, we study the task of learning to push boxes in a simulated two-dimensional environment originally proposed by Mahadevan and Connell (1992). We examine issues such as effectiveness of learning, flexibility of the learning method to adapt to new environments, and effect of the behavior architecture on the ability to learn, and we report results obtained on a large number of simulation runs.

Original languageEnglish (US)
Pages (from-to)365-390
Number of pages26
JournalAdaptive Behavior
Volume5
Issue number3-4
DOIs
StatePublished - Jan 1 1997

Keywords

  • Behavior-based architectures
  • Reinforcement learning
  • Robot learning

Fingerprint Dive into the research topics of 'Measuring the effectiveness of reinforcement learning for behavior-based robots'. Together they form a unique fingerprint.

Cite this