If you are interested in speeding up RL training, welcome to check out our recent paper at #TMLR.
Title: QuaRL: Quantization for Fast and Environmentally Sustainable Reinforcement Learning
Paper: https://t.co/R7RkKW4xrf
Code: https://t.co/sp5l32hnP0
Very excited to share this work that with a simple idea reduces carbon footprint of training RL model by up to 3.8x w/ @Srivatsan91 , @profvjreddi, and other collaborators from @hseas and @DeepMind.
Thanks @Aleksandra, @profvjreddi, @gbarthmaron for your guidance.
Very excited to share our work on applying quantization to speed up RL and reducing carbon footprint. Thanks to my co-authors Max Lam, @sharad24sc,@ZishenW.
C-BRIC researchers and partners can join Zishen Wan for a talk on "Analyzing and Improving Fault Tolerance of Autonomous Navigation Systems" Thurs., Aug. 26 at 11:00am ET/8:00am PT.
Glad to announce my new (first) book 'Robotic Computing on FPGAs'! It's published as Computer Architecture Series by @MorganClaypool. Thanks my collaborators Dr. Shaoshan Liu (PerceptIn), Dr. Bo Yu (PerceptIn), and Prof. Yu Wang (Tsinghua).
https://t.co/Dcva2HEL34
Please join Session-10a (Best of CAL @IEEECAL) at HPCA'21 @HpcaArchConf starting at 12:30 ET Today! Our paper 'The Sky Is Not the Limit: A Visual Performance Model for Cyber-Physical Co-Design in Autonomous Machines' will be presented!
https://t.co/win8noi3tk