Multiagent value iteration algorithms in dynamic programming and reinforcement learning

Research output: Contribution to journalArticlepeer-review

16 Scopus citations


We consider infinite horizon dynamic programming problems, where the control at each stage consists of several distinct decisions, each one made by one of several agents. In an earlier work we introduced a policy iteration algorithm, where the policy improvement is done one-agent-at-a-time in a given order, with knowledge of the choices of the preceding agents in the order. As a result, the amount of computation for each policy improvement grows linearly with the number of agents, as opposed to exponentially for the standard all-agents-at-once method. For the case of a finite-state discounted problem, we showed convergence to an agent-by-agent optimal policy. In this paper, this result is extended to value iteration and optimistic versions of policy iteration, as well as to more general DP problems where the Bellman operator is a contraction mapping, such as stochastic shortest path problems with all policies being proper.

Original languageEnglish (US)
Article number100003
JournalResults in Control and Optimization
StatePublished - Dec 2020

ASJC Scopus subject areas

  • Control and Optimization
  • Applied Mathematics
  • Artificial Intelligence
  • Modeling and Simulation
  • Control and Systems Engineering


Dive into the research topics of 'Multiagent value iteration algorithms in dynamic programming and reinforcement learning'. Together they form a unique fingerprint.

Cite this