TY - JOUR
T1 - Geometric Reinforcement Learning for Robotic Manipulation
AU - Alhousani, Naseem
AU - Saveriano, Matteo
AU - Sevinc, Ibrahim
AU - Abdulkuddus, Talha
AU - Kose, Hatice
AU - Abu-Dakka, Fares J.
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2023
Y1 - 2023
N2 - 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 ( mathcal {G}-RL), to enable agents to learn robotic manipulation skills with non-Euclidean data. Specifically, mathcal {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 mathcal {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 mathcal {G}-RL is more accurate and converges to a better solution than approximating non-Euclidean data.
AB - 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 ( mathcal {G}-RL), to enable agents to learn robotic manipulation skills with non-Euclidean data. Specifically, mathcal {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 mathcal {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 mathcal {G}-RL is more accurate and converges to a better solution than approximating non-Euclidean data.
KW - Learning on manifolds
KW - geometric reinforcement learning
KW - policy optimization
KW - policy search
UR - http://www.scopus.com/inward/record.url?scp=85174855803&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85174855803&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2023.3322654
DO - 10.1109/ACCESS.2023.3322654
M3 - Article
AN - SCOPUS:85174855803
SN - 2169-3536
VL - 11
SP - 111492
EP - 111505
JO - IEEE Access
JF - IEEE Access
ER -