no code implementations • 28 Nov 2020 • Edward Lockhart, Neil Burch, Nolan Bard, Sebastian Borgeaud, Tom Eccles, Lucas Smaira, Ray Smith
We introduce a human-compatible reinforcement-learning approach to a cooperative game, making use of a third-party hand-coded human-compatible bot to generate initial training data and to perform initial evaluation.
1 code implementation • ACM 2009 • Ray Smith, Daria Antonova, Dar-Shyang Lee
We describe efforts to adapt the Tesseract open source OCR engine for multiple scripts and languages.