Sayantan Auddy

Publications

Journals

  1. Sayantan Auddy, Jakob Hollenstein, Matteo Saveriano, Antonio Rodríguez-Sánchez and Justus Piater. Continual Learning from Demonstration of Robotics Skills. Robotics and Autonomous Systems, 2023. Journal track in Conference on Lifelong Learning Agents, 2023. (paper)

  2. Jakob Hollenstein, Sayantan Auddy, Matteo Saveriano, Erwan Renaudo, Justus Piater. Action Noise in Off-Policy Deep Reinforcement Learning: Impact on Exploration and Performance. Transactions on Machine Learning Research, 2022. (paper)

Conferences

  1. Josip Josifovski+, Sayantan Auddy+, Mohammadhossein Malmir, Justus Piater, Alois Knoll and Nicolás Navarro-Guerrero. Continual Domain Randomization. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024. (paper) (Equal contribution +)

  2. Sayantan Auddy, Sven Magg and Stefan Wermter. Hierarchical Control for Bipedal Locomotion using Central Pattern Generators and Neural Networks. IEEE International Conference on Development and Learning and Epigenetic Robotics, 2019. (paper)

  3. Iris Wieser, Sibel Toprak, Andreas Grenzing, Tobias Hinz, Sayantan Auddy, Ethem Can Karaoğuz, Abhilash Chandran, Melanie Remmels, Ahmed El Shinawi, Josip Josifovski, Leena Chennuru Vankadara, Faiz Ul Wahab, Alireza M Bahnemiri, Debasish Sahu, Stefan Heinrich, Nicolás Navarro-Guerrero, Erik Strahl, Johannes Twiefel and Stefan Wermter. A Robotic Home Assistant with Memory Aid Functionality. Joint German/Austrian Conference on Artificial Intelligence, 2016. (paper)

Preprints

  1. Sayantan Auddy, Jakob Hollenstein, Matteo Saveriano, Antonio Rodríguez-Sánchez and Justus Piater. Scalable and Efficient Continual Learning from Demonstration via Hypernetwork-generated Stable Dynamics Model. (paper)

  2. Sayantan Auddy+, Antonio Paolillo+, Justus Piater and Matteo Saveriano. Direct Imitation Learning-based Visual Servoing using the Large Projection Formulation. (paper) (Equal contribution +)

  3. Soubarna Banik, Edvard Avagyan, Sayantan Auddy, Alejandro Mendoza Garcia, and Alois Knoll. PoseGraphNet++: Enriching 3D Human Pose with Orientation Estimation. (paper)

  4. Jakob Hollenstein, Sayantan Auddy, Matteo Saveriano, Erwan Renaudo, Justus Piater. How do Offline Measures for Exploration in Reinforcement Learning behave? (paper)

Workshops

  1. Sayantan Auddy, Sebastian Bergner and Justus Piater. Effect of Optimizer, Initializer, and Architecture of Hypernetworks on Continual Learning from Demonstration. (paper)

  2. Philemon Schöpf, Sayantan Auddy, Jakob Hollenstein, Antonio Rodriguez-Sanchez. Hypernetwork-PPO for Continual Reinforcement Learning. Deep Reinforcement Learning Workshop NeurIPS, 2022. (paper)

  3. Sayantan Auddy, Jakob Hollenstein, Matteo Saveriano, Antonio Rodríguez-Sánchez and Justus Piater. Continual Learning Benchmarks for Antipodal Grasping. Austrian Robotics Workshop, 2022. (paper)

  4. Sayantan Auddy, Jakob Hollenstein, Matteo Saveriano, Antonio Rodríguez-Sánchez and Justus Piater. Can Expressive Posterior Approximations Improve Variational Continual Learning?. Workshop on Lifelong Learning for Long-term Human-Robot Interaction at RO-MAN, 2022. (paper)

  5. Jakob Hollenstein, Matteo Saveriano, Sayantan Auddy, Erwan Renaudo, Justus Piater. How does the type of exploration-noise affect returns and exploration on Reinforcement Learning benchmarks? Austrian Robotics Workshop, 2021. (paper)

Theses

  1. Sayantan Auddy. Hierarchical Control for Bipedal Locomotion using Central Pattern Generators and Neural Networks. Master’s thesis, University of Hamburg, Germany, 2017. (thesis)

Google scholar profile

Home