Creating artificial life forms through evolutionary robotics faces a “chicken and egg” problem: learning to control a complex body is dominated by problems specific to its s...
Abstract— The need for efficient monitoring of spatiotemporal dynamics in large environmental surveillance applications motivates the use of robotic sensors to achieve sufficie...
Amarjeet Singh 0003, Fabio Ramos, Hugh D. Whyte, W...
—The real world is composed of sets of objects that move and morph in both space and time. Useful concepts can be defined in terms of the complex interactions between the multi-...
Matthew Bodenhamer, Samuel Bleckley, Daniel Fennel...
Existing task allocation algorithms generally do not consider the effects of task interaction, such as interference, but instead assume that tasks are independent. That assumptio...
We present new algorithms for inverse optimal control (or inverse reinforcement learning, IRL) within the framework of linearlysolvable MDPs (LMDPs). Unlike most prior IRL algorit...