Co-imitation: Learning Design and Behaviour by Imitation
Keywords:ROB: Learning & Optimization for ROB, ROB: Behavior Learning & Control, ML: Evolutionary Learning, ML: Imitation Learning & Inverse Reinforcement Learning
AbstractThe co-adaptation of robots has been a long-standing research endeavour with the goal of adapting both body and behaviour of a robot for a given task, inspired by the natural evolution of animals. Co-adaptation has the potential to eliminate costly manual hardware engineering as well as improve the performance of systems. The standard approach to co-adaptation is to use a reward function for optimizing behaviour and morphology. However, defining and constructing such reward functions is notoriously difficult and often a significant engineering effort. This paper introduces a new viewpoint on the co-adaptation problem, which we call co-imitation: finding a morphology and a policy that allow an imitator to closely match the behaviour of a demonstrator. To this end we propose a co-imitation methodology for adapting behaviour and morphology by matching state-distributions of the demonstrator. Specifically, we focus on the challenging scenario with mismatched state- and action-spaces between both agents. We find that co-imitation increases behaviour similarity across a variety of tasks and settings, and demonstrate co-imitation by transferring human walking, jogging and kicking skills onto a simulated humanoid.
How to Cite
Rajani, C., Arndt, K., Blanco-Mulero, D., Luck, K. S., & Kyrki, V. (2023). Co-imitation: Learning Design and Behaviour by Imitation. Proceedings of the AAAI Conference on Artificial Intelligence, 37(5), 6200-6208. https://doi.org/10.1609/aaai.v37i5.25764
AAAI Technical Track on Intelligent Robotics