all AI news
Neighborhood Mixup Experience Replay: Local Convex Interpolation for Improved Sample Efficiency in Continuous Control Tasks. (arXiv:2205.09117v1 [cs.LG])
May 20, 2022, 1:11 a.m. | Ryan Sander, Wilko Schwarting, Tim Seyde, Igor Gilitschenski, Sertac Karaman, Daniela Rus
cs.LG updates on arXiv.org arxiv.org
Experience replay plays a crucial role in improving the sample efficiency of
deep reinforcement learning agents. Recent advances in experience replay
propose using Mixup (Zhang et al., 2018) to further improve sample efficiency
via synthetic sample generation. We build upon this technique with Neighborhood
Mixup Experience Replay (NMER), a geometrically-grounded replay buffer that
interpolates transitions with their closest neighbors in state-action space.
NMER preserves a locally linear approximation of the transition manifold by
only applying Mixup between transitions with vicinal …
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
Senior ML Researcher - 3D Geometry Processing | 3D Shape Generation | 3D Mesh Data
@ Promaton | Europe
Analytics Engineer
@ CircleCI | Remote (US), Remote (Canada), San Francisco, Denver
Bilingual Executive Assistant/Data Analyst - (French and English) - Export
@ Dangote Group | Lagos, Lagos, Nigeria
Workday Services Data Lead
@ WPP | Mexico City, Mexico
Business Data Analyst
@ Nordea | Tallinn, EE, 11415
Data Integrity Lead
@ BioNTech SE | Gaithersburg, MD, US, MD 20878