Bhavya Sukhija

• PhD Student
• bhavya.sukhija@inf.ethz.ch
• OAT Y 19
• Linkedln
• External Website
• My research interests lie in the application of reinforcement learning for complex real-world robotic systems. Particularly, I am interested in solving complex tasks with robotic systems which hit the limitations of traditional control schemes. Since I am working directly with robots, sample efficiency and safety of the learning algorithm are of special interest to me. I am part of the Computational Robotics Lab (CRL) led by Prof. Stelian Coros and the Learning & Adaptive Systems (LAS) group led by Prof. Andreas Krause.

---

Publications

2024

Active Few-Shot Fine-Tuning J. Hübotter, B. Sukhija, L. Treven, Y. As, A. Krause In ICLR 2024 Workshop on Bridging the Gap Between Practice and Theory in Deep Learning, 2024 [bibtex] [abstract] [pdf]

2023

Optimistic Active Exploration of Dynamical Systems B. Sukhija, L. Treven, C. Sancaktar, S. Blaes, S. Coros, A. Krause In Proc. Neural Information Processing Systems (NeurIPS), 2023 [bibtex] [abstract] [pdf]

Efficient Exploration in Continuous-time Model-based Reinforcement Learning L. Treven, J. Hübotter, B. Sukhija, F. Dörfler, A. Krause In Proc. Neural Information Processing Systems (NeurIPS), 2023 [bibtex] [abstract] [pdf]

GoSafeOpt: Scalable safe exploration for global optimization of dynamical systems B. Sukhija, M. Turchetta, D. Lindner, A. Krause, S. Trimpe, D. Baumann In Artificial Intelligence Journal (AIJ), 2023 [bibtex] [abstract] [pdf]

Hallucinated Adversarial Control for Conservative Offline Policy Evaluation J. Rothfuss*, B. Sukhija*, T. Birchler*, P. Kassraie, A. Krause In Conference on Uncertainty in Artificial Intelligence (UAI), 2023 [bibtex] [abstract] [pdf]

Gradient-Based Trajectory Optimization With Learned Dynamics B. Sukhija, N. Köhler, M. Zamora, S. Zimmermann, S. Curi, A. Krause, S. Coros In IEEE International Conference on Robotics and Automation (ICRA), 2023 [bibtex] [abstract] [pdf]

Tuning Legged Locomotion Controllers via Safe Bayesian Optimization D. Widmer, D. Kang, B. Sukhija, J. Hübotter, A. Krause, S. Coros In Proc. Conference on Robot Learning (CoRL), 2023 [bibtex] [abstract] [pdf]

Data-Efficient Task Generalization via Probabilistic Model-based Meta Reinforcement Learning A. Bhardwaj, J. Rothfuss, B. Sukhija, Y. As, M. Hutter, S. Coros, A. Krause In arXiv preprint arXiv:2311.07558, 2023 [bibtex] [abstract] [pdf]