Avoiding wireheading with value reinforcement learning

Citation

Everitt, T & Hutter, M 2016, 'Avoiding wireheading with value reinforcement learning', International Conference on Artificial General Intelligence, AGI 2016, ed. B. Steunebrink, P Wang, B. Goertzel, Springer International Publishing AG, Switzerland, pp. 12-22.

Year

2016

ANU Authors

Field of Research

  • Adaptive Agents And Intelligent Robotics

Updated:  18 June 2019 / Responsible Officer:  Director (Research Services Division) / Page Contact:  Researchers