Learning complex locomotion and manipulation tasks presents significant challenges, often requiring extensive engineering of, e.g., reward functions or curricula to provide meaningful feedback to the Reinforcement Learning (RL) algorithm. This paper proposes an intrinsically motivated RL approach to reduce taskspecific engineering. The desired task is encoded in a single sparse reward, i.e., a reward of “+1” is given if the task is achieved. Intrinsic motivation enables learning by guiding exploration toward the sparse reward signal. Specifically, we adapt the idea of Random Network Distillation (RND) to the robotics domain to learn holistic motion control policies involving simultaneous locomotion and manipulation. We investigate opening doors as an exemplary task for robotic applications. A second task involving package manipulation from a table to a bin highlights the generalization capabilities of the presented approach. Finally, the resulting RL policies are executed in realworld experiments on a wheeledlegged robot in biped mode. We experienced no failure in our experiments, which con sisted of opening push doors (over 15 times in a row) and manipulating packages (over 5 times in a row).

Paper: https://openreview.net/pdf?id=QG_ERxt...
Authors: Clemens Schwarke, Victor Klemm, Matthijs van der Boon, Marko Bjelonic, and Marco Hutter

Learn more: https://www.swissmile.com/

Disclaimer: Robot from ANYbotics; customized by ETH Zürich; strictly for research purposes.