Constrained Multiagent Markov Decision Processes: a Taxonomy of Problems and Algorithms

DOI10.1613/jair.1.12233OpenAlexW3134671698MaRDI QIDQ5856487

Erwin Walraven, Frits de Nijs, Mathijs de Weerdt, Matthijs T. J. Spaan

Publication date: 26 March 2021

Published in: Journal of Artificial Intelligence Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1613/jair.1.12233

zbMATH Keywords

Markov decision processesmultiagent systems

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Uses Software

• AlphaZero
• Safety Gym

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Planning and acting in partially observable stochastic domains
• Opportunistic spectrum access in unslotted primary systems
• Maximal mean/standard deviation ratio in an undiscounted MDP
• Optimal policies for controlled Markov chains with a constraint
• Where are the hard knapsack problems?
• Convex Optimization: Algorithms and Complexity
• A Survey of Multi-Objective Sequential Decision-Making
• A Concise Introduction to Decentralized POMDPs
• A Linear Programming Approach to the Cutting-Stock Problem
• Relaxations of Weakly Coupled Stochastic Dynamic Programs
• Resource-Driven Mission-Phasing Techniques for Constrained Agents in Stochastic Environments
• The Complexity of Markov Decision Processes
• The Optimal Control of Partially Observable Markov Processes over the Infinite Horizon: Discounted Costs
• On Finding Optimal Policies for Markov Decision Chains: A Unifying Framework for Mean-Variance-Tradeoffs
• Column Generation Algorithms for Constrained POMDPs
• Markov Decision Processes with Sample Path Constraints: The Communicating Case
• A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
• The Complexity of Decentralized Control of Markov Decision Processes
• A Sufficient Statistic for Influence in Structured Multiagent Environments

This page was built for publication: Constrained Multiagent Markov Decision Processes: a Taxonomy of Problems and Algorithms