
Model-Free Reinforcement Learning with Skew-Symmetric Bilinear Utilities
Author(s) -
Hugo Gilbert,
Bruno Zanuttini,
Paolo Viappiani,
Paul Weng,
Esther Nicart
Publication year - 2016
Publication title -
hal (le centre pour la communication scientifique directe)
Language(s) - English
Resource type - Conference proceedings
Subject(s) - reinforcement learning , computer science , skew , adaptation (eye) , bilinear interpolation , von neumann architecture , convergence (economics) , q learning , decision maker , expected utility hypothesis , mathematical optimization , variety (cybernetics) , reinforcement , function (biology) , decision theory , artificial intelligence , mathematical economics , mathematics , operations research , economics , engineering , telecommunications , computer vision , statistics , physics , structural engineering , evolutionary biology , optics , biology , economic growth , operating system