Hindsight is Only 50/50: Unsuitability of MDP based Approximate POMDP Solvers for Multi-resolution Information Gathering

7 April 2018

Papers citing "Hindsight is Only 50/50: Unsuitability of MDP based Approximate POMDP Solvers for Multi-resolution Information Gathering"

10 / 10 papers shown

Title
Data-driven Planning via Imitation Learning Sanjiban Choudhury M. Bhardwaj S. Arora Ashish Kapoor G. Ranade Sebastian Scherer Debadeepta Dey 82 81 0 17 Nov 2017
Learning to Gather Information via Imitation Sanjiban Choudhury Ashish Kapoor G. Ranade Debadeepta Dey 99 29 0 13 Nov 2016
Learning from the Hindsight Plan -- Episodic MPC Improvement Aviv Tamar G. Thomas Tianhao Zhang Sergey Levine Pieter Abbeel 121 66 0 28 Sep 2016
Perception-aware Path Planning G. Costante Christian Forster J. Delmerico P. Valigi Davide Scaramuzza 35 75 0 13 May 2016
Configuration Lattices for Planar Contact Manipulation Under Uncertainty Michael C. Koval David Hsu N. S. Pollard S. Srinivasa 108 12 0 30 Apr 2016
POMDP-lite for Robust Robot Planning under Uncertainty Min Chen Emilio Frazzoli David Hsu Wee Sun Lee 80 64 0 16 Feb 2016
Learning Deep Control Policies for Autonomous Aerial Vehicles with MPC-Guided Policy Search Tianhao Zhang G. Kahn Sergey Levine Pieter Abbeel 70 427 0 22 Sep 2015
Shared Autonomy via Hindsight Optimization Shervin Javdani S. Srinivasa J. Andrew Bagnell 60 195 0 26 Mar 2015
Online Planning Algorithms for POMDPs Stéphane Ross Joelle Pineau Sébastien Paquet B. Chaib-draa 90 583 0 15 Jan 2014
On the Complexity of Solving Markov Decision Problems Michael L. Littman T. Dean L. Kaelbling 77 585 0 20 Feb 2013