New Algorithms for Collaborative and Adversarial Decision Making in Partially Observable Stochastic Games

Abstract

The project has produced new computational models and algorithms for coordination, prediction and planning in situations involving multiple decision makers that operate over an extended period of time in either collaborative or adversarial domains. This includes the development of the decentralized partially-observable Markov decision process (DEC-POMDP) model, memory-bounded algorithm for solving finite-horizon DEC-POMDPs, sparse representations of agent strategies using finite-state controllers, bounded policy iteration algorithms for infinite-horizon DEC-POMDPs, and algorithms for solving DEC-POMDPs using non-linear optimization methods. The project produced the best existing exact algorithms for these problems as well as scalable approximation techniques and benchmark problems that are now widely used within the multi-agent systems community. The report describes these research accomplishments and provides references to published papers and PhD dissertations that include detailed descriptions of the results.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 14, 2009
Accession Number
ADA495149

Entities

People

  • Shlomo Zilberstein

Organizations

  • University of Massachusetts Amherst

Tags

Communities of Interest

  • Autonomy
  • Human Systems

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Autonomous Agents
  • British Columbia
  • Computer Science
  • Contract Administration
  • Dynamic Programming
  • Evolutionary Algorithms
  • Intelligent Agents
  • Iterations
  • Linear Programming
  • Mathematics
  • Multiagent Systems
  • Operations Research
  • Optimization
  • Students
  • Theses

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Team-Based Human-Centered Cognitive Task Decision Making and Information Performance.