David Mguni
David Mguni
Principal Scientist, Noah's Ark Lab, Huawei
Verified email at
Cited by
Cited by
Decentralised learning in systems with many, many strategic agents
D Mguni, J Jennings, EM de Cote
Proceedings of the AAAI Conference on Artificial Intelligence 32 (1), 2018
Multi-agent determinantal q-learning
Y Yang, Y Wen, J Wang, L Chen, K Shao, D Mguni, W Zhang
ICML 2020, 10757-10766, 2020
Modelling behavioural diversity for learning in open-ended games
NP Nieves, Y Yang, O Slumbers, DH Mguni, Y Wen, J Wang
ICML 2021, Long Oral, 2021
Learning in Nonzero-Sum Stochastic Games with Potentials
D Mguni, Y Wu, Y Du, Y Yang, Z Wang, M Li, Y Wen, J Jennings, J Wang
ICML 2021 139, 7688--7699, 2021
Coordinating the crowd: Inducing desirable equilibria in non-cooperative systems
D Mguni, J Jennings, SV Macua, E Sison, S Ceppi, EM De Cote
AAMAS 2019, 386–394, 2019
Settling the variance of multi-agent policy gradients
JG Kuba, M Wen, L Meng, H Zhang, D Mguni, J Wang, Y Yang
Advances in Neural Information Processing Systems 34, 13458-13470, 2021
On the complexity of computing markov perfect equilibrium in general-sum stochastic games
X Deng, Y Li, DH Mguni, J Wang, Y Yang
National Science Review, 2095-2138, 2021
Online double oracle
LC Dinh, Y Yang, S McAleer, Z Tian, NP Nieves, O Slumbers, DH Mguni, ...
Transactions on Machine Learning Research, 2023
SAUTE RL: Almost Surely Safe Reinforcement Learning Using State Augmentation
A Sootla, AI Cowen-Rivers, T Jafferjee, Z Wang, D Mguni, J Wang, ...
ICML, 2022
A viscosity approach to stochastic differential games of control and stopping involving impulsive control
D Mguni
arXiv preprint arXiv:1803.11432, 2018
LIGS: Learnable Intrinsic-Reward Generation Selection for Multi-Agent Learning
DH Mguni, T Jafferjee, J Wang, N Perez-Nieves, O Slumbers, F Tong, Y Li, ...
ICLR, 2022
Cutting your losses: Learning fault-tolerant control and optimal stopping under adverse risk
D Mguni
arXiv preprint arXiv:1902.05045, 2019
Incentive control for multi-agent systems
D Mguni, S Ceppi, S Macua, EM DE COTE
US Patent App. 17/261,500, 2021
Timing is Everything: Learning to Act Selectively with Costly Actions and Budgetary Constraints
D Mguni, A Sootla, J Ziomek, O Slumbers, Z Dai, K Shao, J Wang
ICLR 2023, 2023
Optimal selection of transaction costs in a dynamic principal-agent problem
D Mguni
arXiv preprint arXiv:1805.01062, 2018
Online Markov Decision Processes with Non-oblivious Strategic Adversary
LC Dinh, DH Mguni, L Tran-Thanh, J Wang, Y Yang
Autonomous Agents and Multi-Agent Systems, 2023
Learning to Shape Rewards using a Game of Two Partners
D Mguni, T Jafferjee, J Wang, N Perez-Nieves, W Song, F Tong, M Taylor, ...
AAAI 2023, 2023
Efficient reinforcement dynamic mechanism design
D Mguni, M Tomczak
GAIW: Games, agents and incentives workshops, at AAMAS, Montreal, Canada, 2019
Duopoly Investment Problems with Minimally Bounded Adjustment Costs
D Mguni
arXiv preprint arXiv:1805.11974, 2018
Optimal capital injections with the risk of ruin: A stochastic differential game of impulse control and stopping approach
D Mguni
arXiv preprint arXiv:1805.01578, 2018
The system can't perform the operation now. Try again later.
Articles 1–20