Geometric Reinforcement Learning For Robotic Manipulation


Creative Commons License

Alhousani N., Saveriano M., Sevinc I., Abdulkuddus T., Köse H., Abu-Dakka F. J.

IEEE Access, vol.11, pp.111492-111505, 2023 (SCI-Expanded) identifier

  • Publication Type: Article / Article
  • Volume: 11
  • Publication Date: 2023
  • Doi Number: 10.1109/access.2023.3322654
  • Journal Name: IEEE Access
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, INSPEC, Directory of Open Access Journals
  • Page Numbers: pp.111492-111505
  • Keywords: geometric reinforcement learning, Learning on manifolds, policy optimization, policy search
  • Istanbul Technical University Affiliated: Yes

Abstract

Reinforcement learning (RL) is a popular technique that allows an agent to learn by trial and error while interacting with a dynamic environment. The traditional Reinforcement Learning (RL) approach has been successful in learning and predicting Euclidean robotic manipulation skills such as positions, velocities, and forces. However, in robotics, it is common to encounter non-Euclidean data such as orientation or stiffness, and failing to account for their geometric nature can negatively impact learning accuracy and performance. In this paper, to address this challenge, we propose a novel framework for RL that leverages Riemannian geometry, which we call Geometric Reinforcement Learning (G-RL), to enable agents to learn robotic manipulation skills with non-Euclidean data. Specifically, G-RL utilizes the tangent space in two ways: a tangent space for parameterization and a local tangent space for mapping to a non-Euclidean manifold. The policy is learned in the parameterization tangent space, which remains constant throughout the training. The policy is then transferred to the local tangent space via parallel transport and projected onto the non-Euclidean manifold. The local tangent space changes over time to remain within the neighborhood of the current manifold point, reducing the approximation error. Therefore, by introducing a geometrically grounded pre- and post-processing step into the traditional RL pipeline, our G-RL framework enables several model-free algorithms designed for Euclidean space to learn from non-Euclidean data without modifications. Experimental results, obtained both in simulation and on a real robot, support our hypothesis that G-RL is more accurate and converges to a better solution than approximating non-Euclidean data.