Nonconvex Policy Search Using Variational Inequalities

DOI10.1162/neco_a_01004zbMath1456.68173OpenAlexW2742739506WikidataQ47327926 ScholiaQ47327926MaRDI QIDQ5380851

Haitham Bou-Ammar, Yusen Zhan, Matthew E. Taylor

Publication date: 6 June 2019

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1162/neco_a_01004

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Variational inequalities (49J40) (H^infty)-control (93B36)

Related Items (1)

Minimum and maximum principle sufficiency for a nonsmooth variational inequality

Uses Software

• AdaGrad

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Policy search for motor primitives in robotics
• Extragradient methods for solving nonconvex variational inequalities
• Sensitivity analysis for variational inequalities
• Finite-dimensional variational inequality and nonlinear complementarity problems: A survey of theory, algorithms and applications
• Projection methods for nonconvex variational inequalities
• Natural actor-critic algorithms
• New approximation schemes for general variational inequalities
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• Some developments in general variational inequalities
• Predictor-corrector methods for general regularized nonconvex variational inequalities
• Introduction to nonlinear and global optimization
• Curvature Measures
• Modification of the extra-gradient method for solving variational inequalities and certain optimization problems
• Local differentiability of distance functions

This page was built for publication: Nonconvex Policy Search Using Variational Inequalities