As learning agents move from research labs to the real world, it is increasingly important that human users, including those without programming skills, be able to teach agents de...
The reward functions that drive reinforcement learning systems are generally derived directly from the descriptions of the problems that the systems are being used to solve. In so...
Shaping functions can be used in multi-task reinforcement learning (RL) to incorporate knowledge from previously experienced tasks to speed up learning on a new task. So far, rese...
— Biped robots based on the concept of (passive) dynamic walking are far simpler than the traditional fullycontrolled walking robots, while achieving a more natural gait and cons...
Shouyi Wang, Jelmer Braaksma, Robert Babuska, Daan...
Continuous state spaces and stochastic, switching dynamics characterize a number of rich, realworld domains, such as robot navigation across varying terrain. We describe a reinfor...
Emma Brunskill, Bethany R. Leffler, Lihong Li, Mic...