A Survey on Policy Search Algorithms for Learning Robot Controllers in a Handful of Trials

Volume: 36, Issue: 2, Pages: 328 - 347
Published: Apr 1, 2020
Abstract
Most policy search (PS) algorithms require thousands of training episodes to find an effective policy, which is often infeasible with a physical robot. This survey article focuses on the extreme other end of the spectrum: how can a robot adapt with only a handful of trials (a dozen) and a few minutes? By analogy with the word “big-data,” we refer to this challenge as “micro-data reinforcement learning.” In this article, we show that a first...
Paper Details
Title
A Survey on Policy Search Algorithms for Learning Robot Controllers in a Handful of Trials
Published Date
Apr 1, 2020
Volume
36
Issue
2
Pages
328 - 347
Citation AnalysisPro
  • Scinapse’s Top 10 Citation Journals & Affiliations graph reveals the quality and authenticity of citations received by a paper.
  • Discover whether citations have been inflated due to self-citations, or if citations include institutional bias.