scientific article; zbMATH DE number 7064064
From MaRDI portal
Publication:5381139
zbMath1489.91032arXiv1905.04926MaRDI QIDQ5381139
Alistair Letcher, Karl Tuyls, Sébastien Racanière, Thore Graepel, Jakob N. Foerster, James Martens, David Balduzzi
Publication date: 7 June 2019
Full work available at URL: https://arxiv.org/abs/1905.04926
Title: zbMATH Open Web Interface contents unavailable due to conflicting licenses.
game theorydynamical systemsHamiltonian mechanicsgradient descentclassical mechanicsdeep learninggenerative adversarial networks
Nonparametric estimation (62G05) Artificial neural networks and deep learning (68T07) Differential games (aspects of game theory) (91A23)
Related Items (12)
Physics-informed neural networks for rarefied-gas dynamics: Poiseuille flow in the BGK approximation ⋮ Zeroth-order single-loop algorithms for nonconvex-linear minimax problems ⋮ Efficient second-order optimization with predictions in differential games ⋮ Learning equilibrium in bilateral bargaining games ⋮ A unified single-loop alternating gradient projection algorithm for nonconvex-concave and convex-nonconcave minimax problems ⋮ Riemannian Hamiltonian Methods for Min-Max Optimization on Manifolds ⋮ Unnamed Item ⋮ Towards multi‐agent reinforcement learning‐driven over‐the‐counter market simulations ⋮ Understanding and Mitigating Gradient Flow Pathologies in Physics-Informed Neural Networks ⋮ Multi-agent reinforcement learning: a selective overview of theories and algorithms ⋮ Training GANs with centripetal acceleration ⋮ Higher-Order Methods for Convex-Concave Min-Max Optimization and Monotone Variational Inequalities
Uses Software
Cites Work
- Statistical ranking and combinatorial Hodge theory
- Hamiltonian games
- Introductory lectures on convex optimization. A basic course.
- Multiagent learning using a variable learning rate
- Learning in games with continuous action sets and unknown payoff functions
- Potential games
- Learning correlated equilibria in games with compact sets of strategies
- First-order methods almost always avoid strict saddle points
- A class of games possessing pure-strategy Nash equilibria
- From Nash Equilibria to Chain Recurrent Sets
- Simple Adaptive Strategies
- Flows and Decompositions of Games: Harmonic and Potential Games
- Multiagent Systems
- Iterative Solution of Nonlinear Equations in Several Variables
- The Complexity of Computing a Nash Equilibrium
- Existence and Uniqueness of Equilibrium Points for Concave N-Person Games
- Equilibrium points in n -person games
- Generalized Nash equilibrium problems
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
This page was built for publication:
