Yarden As | Learning & Adaptive Systems Group

Yarden As

PhD Student
yarden.as@inf.ethz.ch
CAB F 61.1
+41 44 632 71 48
LinkedIn
External Website
How can learning agents use prior knowledge to adapt safely and efficiently to new domains? In my research I try to answer this question by using concepts from reinforcement learning, constrained Markov decision processes, meta-learning and Bayesian inference.

Publications

2026
Safe Exploration via Policy Priors M. Wendl, Y. As, M. Prajapat, A. Pollak, S. Coros, A. Krause In International Conference on Learning Representations (ICLR), 2026 [bibtex] [abstract] [pdf] [blog]
2025
SPiDR: A Simple Approach for Zero-Shot Safety in Sim-to-Real Transfer Y. As, C. Qu, B. Unger, D. Kang, M. van der Hart, L. Shi, S. Coros, A. Wierman, A. Krause In Advances in Neural Information Processing Systems (NeurIPS), 2025 [bibtex] [abstract] [pdf] [blog]
Learning Safety Constraints for Large Language Models X. Chen, Y. As, A. Krause In Forty-second International Conference on Machine Learning, 2025 Spotlight presentation [bibtex] [abstract] [pdf]
ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning Y. As, B. Sukhija, L. Treven, C. Sferrazza, S. Coros, A. Krause In Proc. International Conference on Learning Representations (ICLR), 2025 [bibtex] [abstract] [pdf]
SafeRPlan: Safe deep reinforcement learning for intraoperative planning of pedicle screw placement Y. Ao, H. Esfandiari, F. Carrillo, C. J. Laux, Y. As, R. Li, K. Van Assche, A. Davoodi, N. A. Cavalcanti, M. Farshad, others In Medical Image Analysis, volume 99, 2025 [bibtex] [abstract] [pdf] [doi]
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]
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]
Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning I. Usmanova, Y. As, M. Kamgarpour, A. Krause In Journal of Machine Learning Research, volume 25, 2024 [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]
2022
Constrained Policy Optimization via Bayesian World Models Y. As, I. Usmanova, S. Curi, A. Krause In Proc. International Conference on Learning Representations (ICLR), 2022 Spotlight presentation [bibtex] [abstract] [pdf] [code]