Collection
Multi-agent Dynamic Decision Making and Learning
- Submission status
- Closed
As a large and ever-increasing part of our economic and social interactions move to the cyberspace, data-driven algorithmic decision making by autonomous agents is fast becoming an integral and inseparable part of our lives. These agents are competing in uncertain and volatile environments and must in turn learn aspects thereof, and of each other, in order to dynamically optimize their performance. What’s more, even the humans in the loop are obliged to depend more and more on data-driven signals for their own decision making, e.g., on automated rankings and recommendations. Given the inherently distributed, strategic, dynamic nature of this ethos, learning in dynamic games, with its broad spectrum of modeling and analysis tools, is a prime candidate for providing this endeavour the theoretical underpinnings, with a balance between unification of the mathematical substructure while retaining the distinct flavors and diversity of the competing paradigms. On modeling front, this ranges from dynamic cooperative games to mean field and evolutionary games, and for learning paradigms, from reinforcement learning to learning by imitation.
Editors
-
Konstantin Avrachenkov
INRIA Sophia Antipolis, France
-
Vivek S. Borkar
IIT Bombay, Mumbai, India
-
U. Jayakrishnan Nair
IIT Bombay, Mumbai, India
Articles (15 in this collection)
-
-
Robustness and Sample Complexity of Model-Based MARL for General-Sum Markov Games
Authors
- Jayakumar Subramanian
- Amit Sinha
- Aditya Mahajan
- Content type: OriginalPaper
- Published: 21 January 2023
- Pages: 56 - 88
-
Robust Networked Multiagent Optimization: Designing Agents to Repair Their Own Utility Functions
Authors
- Philip N. Brown
- Joshua H. Seaton
- Jason R. Marden
- Content type: OriginalPaper
- Published: 01 September 2022
- Pages: 187 - 207
-
Robust Utility Design in Distributed Resource Allocation Problems with Defective Agents
Authors
- Bryce L. Ferguson
- Jason R. Marden
- Content type: OriginalPaper
- Published: 20 August 2022
- Pages: 208 - 230
-
Asymptotic Optimality for Decentralised Bandits
Authors
- Conor J. Newton
- Ayalvadi Ganesh
- Henry W. J. Reeve
- Content type: OriginalPaper
- Open Access
- Published: 20 June 2022
- Pages: 307 - 325
-
Multi-Agent Natural Actor-Critic Reinforcement Learning Algorithms
Authors
- Prashant Trivedi
- Nandyala Hemachandra
- Content type: OriginalPaper
- Open Access
- Published: 16 June 2022
- Pages: 25 - 55
-
Q-Learning in Regularized Mean-field Games
Authors
- Berkay Anahtarci
- Can Deha Kariksiz
- Naci Saldi
- Content type: OriginalPaper
- Published: 23 May 2022
- Pages: 89 - 117
-
Reinforcement Learning for Non-stationary Discrete-Time Linear–Quadratic Mean-Field Games in Multiple Populations
Authors
- Muhammad Aneeq uz Zaman
- Erik Miehling
- Tamer BaÅŸar
- Content type: OriginalPaper
- Published: 10 May 2022
- Pages: 118 - 164
-
Coordinated Replenishment Game and Learning Under Time Dependency and Uncertainty of the Parameters
Authors
- Stefanny Ramirez
- Laurence H. van Brandenburg
- Dario Bauso
- Content type: OriginalPaper
- Open Access
- Published: 31 March 2022
- Pages: 326 - 352
-
Dynamic Games Among Teams with Delayed Intra-Team Information Sharing
Authors (first, second and last of 5)
- Dengwang Tang
- Hamidreza Tavafoghi
- Demosthenis Teneketzis
- Content type: OriginalPaper
- Published: 14 February 2022
- Pages: 353 - 411
-
Where Do Mistakes Lead? A Survey of Games with Incompetent Players
Authors
- Thomas Graham
- Maria Kleshnina
- Jerzy A. Filar
- Content type: OriginalPaper
- Open Access
- Published: 10 February 2022
- Pages: 231 - 264
-
Continuous Time Learning Algorithms in Optimization and Game Theory
Authors
- Sylvain Sorin
- Content type: OriginalPaper
- Published: 31 January 2022
- Pages: 3 - 24
-
Provably Efficient Reinforcement Learning in Decentralized General-Sum Markov Games
Authors
- Weichao Mao
- Tamer BaÅŸar
- Content type: OriginalPaper
- Published: 05 January 2022
- Pages: 165 - 186
-
Opinion Dynamics Control in a Social Network with a Communication Structure
Authors (first, second and last of 4)
- Hui Jiang
- Vladimir V. Mazalov
- Chen Wang
- Content type: OriginalPaper
- Published: 26 November 2021
- Pages: 412 - 434
-
Learning in Games with Cumulative Prospect Theoretic Preferences
Authors
- Soham R. Phade
- Venkat Anantharam
- Content type: OriginalPaper
- Published: 02 August 2021
- Pages: 265 - 306