Near-optimal polynomial time algorithm for learning in certain classes of stochastic games

Ronen I. Brafman, Moshe Tennenholtz

Research output: Contribution to journalArticlepeer-review

20 Scopus citations


We present a new algorithm for polynomial time learning of optimal behavior in single-controller stochastic games. This algorithm incorporates and integrates important recent results of Kearns and Singh in reinforcement learning and of Monderer and Tennenholtz in repeated games. In stochastic games, the agent must cope with the existence of an adversary whose actions can be arbitrary. In particular, this adversary can withhold information about the game matrix by refraining from (or rarely) performing certain actions. This forces upon us an exploration versus exploitation dilemma more complex than in Markov decision processes in which, given information about particular parts of a game matrix, the agent must decide how much effort to invest in learning the unknown parts of the matrix. We present a polynomial time algorithm that addresses these issues in the context of the class of single controller stochastic games, providing the agent with near-optimal return.

Original languageEnglish
Pages (from-to)31-47
Number of pages17
JournalArtificial Intelligence
Issue number1
StatePublished - 1 Jan 2000

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language
  • Artificial Intelligence


Dive into the research topics of 'Near-optimal polynomial time algorithm for learning in certain classes of stochastic games'. Together they form a unique fingerprint.

Cite this