Fetching the paper…
Reading the bibliography…
In this paper, we apply the idea of fictitious play to design deep neural networks (DNNs), and develop deep learning theory and algorithms for computing the Nash equilibrium of asymmetric $N$-player non-zero-sum stochastic differential games, for which we refer as \emph{deep fictitious play}, a multi-stage learning process.
Deep fictitious play for finding markovian Nash equilibrium in multi-agent games
J. Han and R. Hu · 1912
Earlier work this paper cites.
Some notes on computation of games solutions
G. W. Brown · 1949
Earlier work this paper cites.
Iterative solution of games by fictitious play
G. W. Brown · 1951
Earlier work this paper cites.
An iterative method of solving a game
J. Robinson · 1951
Earlier work this paper cites.
On the convergence of the learning process in a 2 × \times 2 non-zero-sum two-person game
K. Miyasawa · 1961
Earlier work this paper cites.
Some topics in two-person games
Lloyd Shapley · 1964
Earlier work this paper cites.
Approximations by superpositions of a sigmoidal function
G. Cybenko · 1989
Earlier work this paper cites.
Adapted solution of a backward stochastic differential equation
E. Pardoux and S. Peng · 1990
Earlier work this paper cites.
Approximation capabilities of multilayer feedforward networks
K. Hornik · 1991
Earlier work this paper cites.
On the representation of continuous functions of several variables as superpositions of continuous functions of one variable and addition
A.N. Kolmogorov · 1991
Earlier work this paper cites.
Adaptive and sophisticated learning in normal form games
P. Milgrom and J. Roberts · 1991
Earlier work this paper cites.
Three problems in learning mixed-strategy Nash equilibria
J. S. Jordan · 1993
Earlier work this paper cites.
A 2 × \times 2 game without the fictitious play property
D. Monderer and A. Sela · 1996
Earlier work this paper cites.
Fictitious play property for games with identical interests
D. Monderer and L. S. Shapley · 1996
Earlier work this paper cites.
Potential games
D. Monderer and L. S. Shapley · 1996
Earlier work this paper cites.
Fictitious play and no-cycling conditions
D. Monderer and A. Sela · 1997
Earlier work this paper cites.
On the nonconvergence of fictitious play in coordination games
D. P. Foster and H. P. Young · 1998
Earlier work this paper cites.
A learning approach to auctions
S. Hon-Snir, D. Monderer, and A. Sela · 1998
Earlier work this paper cites.
On the convergence of fictitious play
V. Krishna and T. Sjöström · 1998
Earlier work this paper cites.
Forward-backward stochastic differential equations and their applications
J. Ma, J.-M. Morel, and J. Yong · 1999
Earlier work this paper cites.
Forward-backward stochastic differential equations and quasilinear parabolic PDEs
E. Pardoux and S. Tang · 1999
Earlier work this paper cites.
Fully coupled forward-backward stochastic differential equations and applications to optimal control
S. Peng and Z. Wu · 1999
Cited alongside, same era.
Approximation theory of the MLP model in neural networks
A. Pinkus · 1999
Cited alongside, same era.
On the global convergence of stochastic fictitious play
J. Hofbauer and W. H. Sandholm · 2002
Cited alongside, same era.
Evolutionary dynamics and extensive form games
R. Cressman and C. Ansell · 2003
Cited alongside, same era.
Fictitious play in 2 × \times n games
U. Berger · 2005
Cited alongside, same era.
Large population stochastic dynamic games: closed-loop McKean-Vlasov systems and the Nash certainty equivalence principle
M. Huang, R. P. Malhamé, and P. E. Caines · 2006
Cited alongside, same era.
On well-posedness of forward-backward SDEs–A unified approach
J. Ma, Z. Wu, D. Zhang, and J. Zhang · 2015
Later among the works it cites.
Incorporating Nesterov momentum into Adam
T. Dozat · 2016
Later among the works it cites.
Deep learning approximation for stochastic control problems
J. Han and W. E · 2016
Later among the works it cites.
Deep reinforcement learning from self-play in imperfect-information games
J. Heinrich and D. Silver · 2016
Later among the works it cites.
Learning in mean field games: the fictitious play
P. Cardaliaguet and S. Hadikhanloo · 2017
Later among the works it cites.
Probabilistic Theory of Mean Field Games with Applications I
R. Carmona and F. Delarue · 2017
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Jeux à champ moyen. I. Le cas stationnaire
J.-M. Lasry and P.-L. Lions · 2006
Cited alongside, same era.
Jeux à champ moyen. II. Horizon fini et contrôle optimal
J.-M. Lasry and P.-L. Lions · 2006
Cited alongside, same era.
Brown’s original fictitious play
U. Berger · 2007
Cited alongside, same era.
Large-population cost-coupled LQG problems with nonuniform agents: individual-mass behavior and decentralized ϵ \epsilon -Nash equilibria
M. Huang, P. E. Caines, and R. P. Malhamé · 2007
Cited alongside, same era.
Mean field games
J.-M. Lasry and P.-L. Lions · 2007
Cited alongside, same era.
Approximate Dynamic Programming: Solving the curses of dimensionality
W. B. Powell · 2007
Cited alongside, same era.
Probabilistic Theory of Mean Field Games with Applications II
R. Carmona and F. Delarue · 2017
Later among the works it cites.
Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
W. E, J. Han, and A. Jentzen · 2017
Later among the works it cites.
A unified game-theoretic approach to multiagent reinforcement learning
M. Lanctot, V. Zambaldi, A. Gruslys, A. Lazaridou, K. Tuyls, J. Pérolat, D. Silver, and T. Graepel · 2017
Later among the works it cites.
Backward Stochastic Differential Equations: From Linear to Fully Nonlinear Theory
J. Zhang · 2017
Later among the works it cites.
A. Bachouch, C. Huré, N. Langrené, and H. Pham · 2018
Later among the works it cites.
Stable solutions in potential mean field game systems
A. Briani and P. Cardaliaguet · 2018
Later among the works it cites.
Solving high-dimensional partial differential equations using deep learning
J. Han, A. Jentzen, and W. E · 2018
Later among the works it cites.
C. Huré, H. Pham, A. Bachouch, and N. Langrené · 2018
Later among the works it cites.
Decentralised learning in systems with many, many strategic agents
D. Mguni, J. Jennings, and E. M. de Cote · 2018
Later among the works it cites.
On the convergence of Adam and beyond
S. J. Reddi, S. Kale, and S. Kumar · 2018
Later among the works it cites.
Deep learning-based methods for stochastic control problems with delay
J. Han and R. Hu · 2020
Closest in time.
Convergence of deep fictitious play for stochastic differential games
J. Han, R. Hu, and J. Long · 2020
Closest in time.
Convergence of the deep BSDE method for coupled FBSDEs
J. Han and J. Long · 2020
Closest in time.
Convergence to the mean field game limit: A case study
M. Nutz, J. San Martin, and X. Tan · 2020
Closest in time.