Fast rates for online learning in Linearly Solvable Markov Decision
Processes

v1v2 (latest)

Fast rates for online learning in Linearly Solvable Markov Decision Processes

21 February 2017

ArXiv (abs)PDF HTML

Papers citing "Fast rates for online learning in Linearly Solvable Markov Decision Processes"

5 / 5 papers shown

Title
RETRO: Reactive Trajectory Optimization for Real-Time Robot Motion Planning in Dynamic Environments Apan Dastider Hao Fang Mingjie Lin 86 4 0 03 Oct 2023
When is Particle Filtering Efficient for Planning in Partially Observed Linear Dynamical Systems? S. Du Wei Hu Zhiyuan Li Ruoqi Shen Zhao Song Jiajun Wu 58 1 0 10 Jun 2020
Online Linear Quadratic Control Alon Cohen Avinatan Hassidim Tomer Koren N. Lazić Yishay Mansour Kunal Talwar 95 151 0 19 Jun 2018
Model-Free Linear Quadratic Control via Reduction to Expert Prediction Yasin Abbasi-Yadkori N. Lazić Csaba Szepesvári OffRL 106 96 0 17 Apr 2018
A unified view of entropy-regularized Markov decision processes Gergely Neu Anders Jonsson Vicencc Gómez 118 264 0 22 May 2017