| Document Date: 2012-07-28 19:03:16
Open Document File Size: 1,02 MBShare Result on Facebook
Company NTL / MIT Press / / / Facility University of California Press / / IndustryTerm multicore processors / reinforcement learning algorithm / baseline convergence algorithm / policy iteration algorithm / partial solution / asynchronous convergence algorithm / explaining our parallelized algorithm / convergence algorithm / parallel algorithm / partial solutions / correct solution / naive solution / / Organization MIT / University of California Press / Pattern Analysis and Machine Intelligence / / Person B. Van Roy / Job Pool Thread Job Runnable / Proc / Jonathan T. Barron / Dave S. Golland Nicholas / / Position Queue Thread pool Scheduler / round-robin scheduler / Scheduling Architecture The scheduler / scheduler / naive scheduler / / ProgrammingLanguage MATLAB / Java / / PublishedMedium IEEE Transactions on Pattern Analysis and Machine Intelligence / the Communicator / / Technology asynchronous convergence algorithm / artificial intelligence / Java / convergence algorithm / parallel algorithm / baseline convergence algorithm / non-parallelized algorithm / multicore processors / simulation / reinforcement learning algorithm / same algorithm / policy iteration algorithm / shared memory / /
SocialTag |
Parallelizing Reinforcement Learning Jonathan T. Barron Dave S. Golland Nicholas J. Hay