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 …

Smarts: An open-source scalable multi-agent rl training school for autonomous driving

M Zhou, J Luo, J Villella, Y Yang… - … on robot learning, 2021 - proceedings.mlr.press
Interaction is fundamental in autonomous driving (AD). Despite more than a decade of
intensive R&D in AD, how to dynamically interact with diverse road users in various contexts …

When physics meets machine learning: A survey of physics-informed machine learning

C Meng, S Seo, D Cao, S Griesemer, Y Liu - arxiv preprint arxiv …, 2022 - arxiv.org
Physics-informed machine learning (PIML), referring to the combination of prior knowledge
of physics, which is the high level abstraction of natural phenomenons and human …

Bi-level actor-critic for multi-agent coordination

H Zhang, W Chen, Z Huang, M Li, Y Yang… - Proceedings of the AAAI …, 2020 - aaai.org
Coordination is one of the essential problems in multi-agent systems. Typically multi-agent
reinforcement learning (MARL) methods treat agents equally and the goal is to solve the …

Modelling bounded rationality in multi-agent interactions by generalized recursive reasoning

Y Wen, Y Yang, R Luo, J Wang - arxiv preprint arxiv:1901.09216, 2019 - arxiv.org
Though limited in real-world decision making, most multi-agent reinforcement learning
(MARL) models assume perfectly rational agents--a property hardly met due to individual's …

Model-based multi-agent policy optimization with adaptive opponent-wise rollouts

W Zhang, X Wang, J Shen, M Zhou - arxiv preprint arxiv:2105.03363, 2021 - arxiv.org
This paper investigates the model-based methods in multi-agent reinforcement learning
(MARL). We specify the dynamics sample complexity and the opponent sample complexity …

Inducing stackelberg equilibrium through spatio-temporal sequential decision-making in multi-agent reinforcement learning

B Zhang, L Li, Z Xu, D Li, G Fan - arxiv preprint arxiv:2304.10351, 2023 - arxiv.org
In multi-agent reinforcement learning (MARL), self-interested agents attempt to establish
equilibrium and achieve coordination depending on game structure. However, existing …

Entropy regularized actor-critic based multi-agent deep reinforcement learning for stochastic games

D Hao, D Zhang, Q Shi, K Li - Information Sciences, 2022 - Elsevier
Multi-agent reinforcement learning (MARL) is an abstract framework modeling a dynamic
environment that involves multiple learning and decision-making agents, each of which tries …

Learning to play sequential games versus unknown opponents

PG Sessa, I Bogunovic… - Advances in neural …, 2020 - proceedings.neurips.cc
We consider a repeated sequential game between a learner, who plays first, and an
opponent who responds to the chosen action. We seek to design strategies for the learner to …

Multi-view reinforcement learning

M Li, L Wu, J Wang… - Advances in neural …, 2019 - proceedings.neurips.cc
This paper is concerned with multi-view reinforcement learning (MVRL), which allows for
decision making when agents share common dynamics but adhere to different observation …