Grounded Action Transformation for Robot Learning in Simulation

No. 1: Thirty-First AAAI Conference On Artificial Intelligence

Volume

Proceedings of the AAAI Conference on Artificial Intelligence, 31

Student Abstract Track

Robot learning in simulation is a promising alternative to the prohibitive sample cost of learning in the physical world. Unfortunately, policies learned in simulation often perform worse than hand-coded policies when applied on the physical robot. This paper proposes a new algorithm for learning in simulation Ñ Grounded Action Transformation Ñ and applies it to learning of humanoid bipedal locomotion. Our approach results in a 43.27% improvement in forward walk velocity compared to a state-of-the art hand-coded walk.

10.1609/aaai.v31i1.11124