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

When to Sense and Control? A Time-adaptive Approach for Continuous-Time RL L. Treven, B. Sukhija, Y. As, F. Dörfler, A. Krause In Advances in Neural Information Processing Systems (NeurIPS), 2024 [bibtex] [abstract] [pdf]

NeoRL: Efficient Exploration for Nonepisodic RL B. Sukhija, L. Treven, F. Dörfler, S. Coros, A. Krause In Advances in Neural Information Processing Systems (NeurIPS), 2024 Spotlight [bibtex] [abstract] [pdf]

Transductive Active Learning: Theory and Applications J. Hübotter, B. Sukhija, L. Treven, Y. As, A. Krause In Proc. Neural Information Processing Systems (NeurIPS), 2024 Oral presentation at Aligning Reinforcement Learning Experimentalists and Theorists Workshop at ICML [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 IEEE Robotics and Automation Letters, IEEE, 2024 [bibtex] [abstract] [pdf]

Bridging the Sim-to-Real Gap with Bayesian Inference J. Rothfuss*, B. Sukhija*, L. Treven*, F. Dörfler, S. Coros, A. Krause In Proc. of the IEEE Int. Conf. on Intelligent Robots and Systems (IROS), 2024 Oral presentation [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]

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]