Deep RL at Scale: Sorting Waste in Office Buildings with a Fleet of Mobile Manipulators.
Alexander HerzogKanishka RaoKarol HausmanYao LuPaul WohlhartMengyuan YanJessica LinMontserrat Gonzalez ArenasTed XiaoDaniel KapplerDaniel HoJarek RettinghouseYevgen ChebotarKuang-Huei LeeKeerthana GopalakrishnanRyan JulianAdrian LiChuyuan Kelly FuBob WeiSangeetha RameshKhem HoldenKim KleivenDavid RendlemanSean KirmaniJeff BinghamJonathan WeiszYing XuWenlong LuMatthew BenniceCody FongDavid DoJessica LamYunfei BaiBenjie HolsonMichael QuinlanNoah BrownMrinal KalakrishnanJulian IbarzPeter PastorSergey LevinePublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- mobile phone
- adaptive control
- path planning
- mobile devices
- scale space
- vehicle routing problem
- multi agent
- office automation
- mobile applications
- mobile environments
- aerial images
- urban areas
- environmental impact
- learning classifier systems
- mobile networks
- mobile computing
- mobile technologies
- mobile users
- function approximation
- robotic systems
- markov decision processes
- context aware