Distributed reinforcement learning based on factored action-spaces

Shahar Cohen*, Oded Maimón, Evgeni Khmelnitsky

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review


This paper addresses the decision-making mechanism, for controlling Markov Decision Processes (MDPs) with factored action-spaces. The paper proposes a simple decision-making approach, which decomposes a multidimensional action-space into its dimensions and distributes the dimensions amongst multiple autonomous agents. A distinct Q-function is defined for each agent, and a Reinforcement Learning (RL) algorithm, which uses the decision-making approach, is proposed. The algorithm maintains estimations that converge to the agents' Q-functions. It is shown that by distributing the decision-making, and due to the factored action-space, new opportunities for representation abstractions emerge. The paper's contribution is illustrated, using a navigation task that involves three robots.

Original languageEnglish
Pages (from-to)188-193
Number of pages6
JournalProceedings of the IASTED International Conference on Intelligent Systems and Control
StatePublished - 2006
Event9th IASTED International Conference on Intelligent Systems and Control, ISC 2006 - Honolulu, HI, United States
Duration: 14 Aug 200616 Aug 2006


  • Distributed reinforcement-learning
  • Factored MDPs
  • Representation abstraction


Dive into the research topics of 'Distributed reinforcement learning based on factored action-spaces'. Together they form a unique fingerprint.

Cite this