Evaluating Strategic Structures in Multi-Agent Inverse Reinforcement Learning

DOI10.1613/jair.1.12594OpenAlexW3195130932MaRDI QIDQ5154749

Julien Perolat, Yoram Bachrach, Andrea Tacchetti, Justin Fu

Publication date: 5 October 2021

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

Full work available at URL: https://doi.org/10.1613/jair.1.12594

zbMATH Keywords

game theoryreinforcement learningmultiagent systems

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Uses Software

• Adam
• Libratus

Cites Work

• Unnamed Item
• Negotiating team formation using deep reinforcement learning
• Learning payoff functions in infinite games
• Extensive-Form Correlated Equilibrium: Definition and Computational Complexity
• Inverse Game Theory: Learning Utilities in Succinct Games
• Mechanism Design by an Informed Principal
• The Power of Verification for Greedy Mechanism Design
• DeepStack: Expert-level artificial intelligence in heads-up no-limit poker
• Superhuman AI for heads-up no-limit poker: Libratus beats top professionals
• Multi-agent Inverse Reinforcement Learning for Certain General-sum Stochastic Games
• Finding Optimal Solutions for Voting Game Design Problems
• Identification of Standard Auction Models
• Principles and Practice of Constraint Programming – CP 2003

This page was built for publication: Evaluating Strategic Structures in Multi-Agent Inverse Reinforcement Learning