Co-Imitation: Learning Design and Behaviour by ImitationDownload PDF

08 Oct 2022, 17:47 (modified: 09 Dec 2022, 14:31)Deep RL Workshop 2022Readers: Everyone
Keywords: imitation learning, co-adaptation, reinforcement learning
TL;DR: We show how to adapt both the behaviour and the design of a robot based on expert demonstrations
Abstract: The co-adaptation of robots has been a long-standing research endeavour with the goal of adapting both body and behaviour of a system 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.
Supplementary Material: zip
0 Replies

Loading