论文信息 - Playing with symmetry with neural networks

Playing with symmetry with neural networks

Finding the optimum design of a complex auction is a challenging and important economic problem. Multi-agent deep learning can help find equilibria by making use of inherent symmetries in bidding strategies.

David C. Parkes

[1] Oleg V. Baranov,et al. Core-selecting auctions with incomplete information , 2020, Int. J. Game Theory.

[2] J. Jordan. Three Problems in Learning Mixed-Strategy Nash Equilibria , 1993 .

[3] S. Shankar Sastry,et al. On Gradient-Based Learning in Continuous Games , 2018, SIAM J. Math. Data Sci..

[4] Martin Bichler,et al. Learning equilibria in symmetric auction games using artificial neural networks , 2021, Nature Machine Intelligence.