Back to Results
First PageMeta Content
Dynamic programming / Stochastic control / Markov models / Partially observable Markov decision process / Reinforcement learning / Markov decision process / Automated planning and scheduling / Action selection / Neurorobotics / Statistics / Markov processes / Artificial intelligence


ORIGINAL RESEARCH ARTICLE published: 06 January 2014 doi: fnbotNEUROROBOTICS
Add to Reading List

Document Date: 2014-01-13 11:29:10

Open Document

File Size: 1,67 MB

Share Result on Facebook

City

Lugano / Manno / /

Company

Sony / /

/

Facility

Dalle Molle Institute / National Tsing-Hua University / University of Skövde / /

IndustryTerm

pre-processing step / considerable energy / iCub hardware / obvious solution / real time / embedded control systems / post-processing / robotic hardware / query algorithms / path planning algorithms / dynamical systems / online learning experiments / learning algorithms / actual iCub hardware / /

Organization

Italian National Research Council / Dalle Molle Institute / University of Skövde / National Tsing-Hua University / /

Person

Alexander Förster / Anthony F. Morse / Mikhail Frank / Federico II / Alberto Finzi / /

Position

motion planner / single curious MDP planner / low-level controller / the planner / curious planner / agent/controller / low-level reactive controller / resolution complete planner / PRM planner / antecedent PRM planner / MDP planner / path planner / planner to control the hardware / planner / head / embodied planner / controller / /

Technology

Observation Algorithm / artificial intelligence / path planning algorithms / RL algorithms / Planning algorithms / query algorithms / simulation / RL algorithm / REINFORCEMENT LEARNING Algorithm / /

URL

www.frontiersin.org / /

SocialTag