A Concise Introduction to Decentralized POMDPs

This book introduces multiagent planning under uncertainty as formalized by decentralized partially observable Markov decision processes (Dec-POMDPs). The intended audience is researchers and graduate students working in the fields of artificial intelligence related to sequential decision making: reinforcement learning, decision-theoretic planning for single agents, classical multiagent planning, decentralized control, and operations research.

First book dedicated to this topic Suitable for researchers and graduate students in AI Assumes prior familiarity with agents, probability, and game theory Includes supplementary material: sn.pub/extras

Inhalt
Multiagent Systems Under Uncertainty.- The Decentralized POMDP Framework.- Finite-Horizon Dec-POMDPs.- Exact Finite-Horizon Planning Methods.- Approximate and Heuristic Finite-Horizon Planning Methods.- Infinite-Horizon Dec-POMDPs.- Infinite-Horizon Planning Methods: Discounted Cumulative Reward.- Infinite-Horizon Planning Methods: Average Reward.- Further Topics.