Reinforcement learning on a futures market simulator

Koichi Moriyama, Mitsuhiro Matsumoto, Ken Ichi Fukui, Satoshi Kurihara, Masayuki Numao

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)


In recent years, market forecasting by machine learning methods has been flourishing. Most existing works use a past market data set, because they assume that each trader's individual decisions do not affect market prices at all. Meanwhile, there have been attempts to analyze economic phenomena by constructing virtual market simulators, in which human and artificial traders really make trades. Since prices in a market are, in fact, determined by every trader's decisions, a virtual market is more realistic, and the above assumption does not apply. In this work, we design several reinforcement learners on the futures market simulator U-Mart (Unreal Market as an Artificial Research Testbed) and compare our learners with the previous champions of U-Mart competitions empirically.

Original languageEnglish
Pages (from-to)1136-1153
Number of pages18
JournalJournal of Universal Computer Science
Issue number7
Publication statusPublished - 2008
Externally publishedYes


  • Market simulation
  • Reinforcement learning

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)


Dive into the research topics of 'Reinforcement learning on a futures market simulator'. Together they form a unique fingerprint.

Cite this