An overview of multi-agent reinforcement learning from game theoretical perspective

Y Yang, J Wang - arxiv preprint arxiv:2011.00583, 2020 - arxiv.org
Following the remarkable success of the AlphaGO series, 2019 was a booming year that
witnessed significant advances in multi-agent reinforcement learning (MARL) techniques …

Cognitive radio: brain-empowered wireless communications

S Haykin - IEEE journal on selected areas in communications, 2005 - ieeexplore.ieee.org
Cognitive radio is viewed as a novel approach for improving the utilization of a precious
natural resource: the radio electromagnetic spectrum. The cognitive radio, built on a …

A unified game-theoretic approach to multiagent reinforcement learning

M Lanctot, V Zambaldi, A Gruslys… - Advances in neural …, 2017 - proceedings.neurips.cc
There has been a resurgence of interest in multiagent reinforcement learning (MARL), due
partly to the recent success of deep neural networks. The simplest form of MARL is …

OpenSpiel: A framework for reinforcement learning in games

M Lanctot, E Lockhart, JB Lespiau, V Zambaldi… - arxiv preprint arxiv …, 2019 - arxiv.org
OpenSpiel is a collection of environments and algorithms for research in general
reinforcement learning and search/planning in games. OpenSpiel supports n-player (single …

A survey on algorithms for Nash equilibria in finite normal-form games

H Li, W Huang, Z Duan, DH Mguni, K Shao… - Computer Science …, 2024 - Elsevier
Nash equilibrium is one of the most influential solution concepts in game theory. With the
development of computer science and artificial intelligence, there is an increasing demand …

Open-ended learning in symmetric zero-sum games

D Balduzzi, M Garnelo, Y Bachrach… - International …, 2019 - proceedings.mlr.press
Zero-sum games such as chess and poker are, abstractly, functions that evaluate pairs of
agents, for example labeling them 'winner'and 'loser'. If the game is approximately transitive …

A unified approach to reinforcement learning, quantal response equilibria, and two-player zero-sum games

S Sokota, R D'Orazio, JZ Kolter, N Loizou… - arxiv preprint arxiv …, 2022 - arxiv.org
This work studies an algorithm, which we call magnetic mirror descent, that is inspired by
mirror descent and the non-Euclidean proximal gradient algorithm. Our contribution is …

Towards unifying behavioral and response diversity for open-ended learning in zero-sum games

X Liu, H Jia, Y Wen, Y Hu, Y Chen… - Advances in …, 2021 - proceedings.neurips.cc
Measuring and promoting policy diversity is critical for solving games with strong non-
transitive dynamics where strategic cycles exist, and there is no consistent winner (eg, Rock …

Modelling behavioural diversity for learning in open-ended games

N Perez-Nieves, Y Yang, O Slumbers… - International …, 2021 - proceedings.mlr.press
Promoting behavioural diversity is critical for solving games with non-transitive dynamics
where strategic cycles exist, and there is no consistent winner (eg, Rock-Paper-Scissors) …

A generalized training approach for multiagent learning

P Muller, S Omidshafiei, M Rowland, K Tuyls… - arxiv preprint arxiv …, 2019 - arxiv.org
This paper investigates a population-based training regime based on game-theoretic
principles called Policy-Spaced Response Oracles (PSRO). PSRO is general in the sense …