no code implementations • 23 Aug 2019 • Patrick Varin, Lev Grossman, Scott Kuindersma
Designing reinforcement learning (RL) problems that can produce delicate and precise manipulation policies requires careful choice of the reward function, state, and action spaces.
no code implementations • NeurIPS 2010 • George Konidaris, Scott Kuindersma, Roderic Grupen, Andrew G. Barto
We demonstrate that CST constructs an appropriate skill tree that can be further refined through learning in a challenging continuous domain, and that it can be used to segment demonstration trajectories on a mobile manipulator into chains of skills where each skill is assigned an appropriate abstraction.