Publications

Preprints

  1. Preprint
    Information Theoretic Approach for Locomotion
    Noam Smilovich, Daniel Polani, and Stas Tiomkin
    Preprint, 2026
  2. Preprint
    arXiv
    Multi-Agent Empowerment and Emergence of Complex Behavior in Groups
    Tristan Shah, Ilya Nemenman, Daniel Polani, and Stas Tiomkin
    arXiv preprint, 2026
  3. Preprint
    arXiv
    Emergence of Physical Intelligence via Controllable Information Production
    Tristan Shah and Stas Tiomkin
    arXiv preprint, 2026
  4. Preprint
    arXiv
    Latent Generative Modeling of Random Fields from Limited Training Data
    James E. Warner, Tristan A. Shah, Patrick E. Leser, Geoffrey F. Bomarito, Joshua D. Pribe, and Michael C. Stanley
    arXiv preprint, 2025

Selected Publications

  1. Royal Society
    arXiv
    Goals and the Structure of Experience
    Nadav Amir, Stas Tiomkin, and Angela Langdon
    Philosophical Transactions of the Royal Society A, 2025
  2. J. Phys. Complexity
    DOI
    Process Empowerment for Robust Intrinsic Motivation
    Stas Tiomkin, Christoph Salge, and Daniel Polani
    Journal of Physics: Complexity, 2025
  3. AAAI
    arXiv
    Bootstrapped Reward Shaping
    Jacob Adamczyk, Volodymyr Makarenko, Stas Tiomkin, and Rahul V. Kulkarni
    In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2025
  4. ICRA
    arXiv
    SuPLE: Robot Learning with Lyapunov Rewards
    Phu Nguyen, Daniel Polani, and Stas Tiomkin
    In IEEE International Conference on Robotics and Automation (ICRA), 2025
  5. ICRA
    arXiv IEEE
    Acoustic Wave Manipulation Through Sparse Robotic Actuation
    Tristan Shah, Noam Smilovich, S. Gerges, Feruza Amirkulova, and Stas Tiomkin
    In IEEE International Conference on Robotics and Automation (ICRA), 2025
  6. PRX Life
    arXiv
    Intrinsic Motivation in Dynamical Control Systems
    Stas Tiomkin, Ilya Nemenman, Daniel Polani, and Naftali Tishby
    PRX Life, 2024
    Selected as one of five spotlight papers; featured at the Global Physics Summit, March 2025.
  7. UAI
    arXiv
    Bounding the Optimal Value Function in Compositional Reinforcement Learning
    Jacob Adamczyk, Volodymyr Makarenko, Argenis Arriojas, Stas Tiomkin, and Rahul V. Kulkarni
    In Conference on Uncertainty in Artificial Intelligence (UAI), 2023
  8. UAI
    PMLR
    Bayesian Inference Approach for Entropy Regularized Reinforcement Learning with Stochastic Dynamics
    Argenis Arriojas, Jacob Adamczyk, Stas Tiomkin, and Rahul V. Kulkarni
    In Conference on Uncertainty in Artificial Intelligence (UAI), 2023
  9. AAAI
    arXiv
    Utilizing Prior Solutions for Reward Shaping and Composition in Entropy-Regularized Reinforcement Learning
    Jacob Adamczyk, Argenis Arriojas, Stas Tiomkin, and Rahul V. Kulkarni
    In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2023
  10. Phys. Rev. Research
    arXiv
    Entropy Regularized Reinforcement Learning Using Large Deviation Theory
    Argenis Arriojas, Jacob Adamczyk, Stas Tiomkin, and Rahul V. Kulkarni
    Physical Review Research, 2023
  11. IROS
    arXiv
    Multi-Objective Policy Gradients with Topological Constraints
    Kyle Hollins Wray, Stas Tiomkin, Mykel J. Kochenderfer, and Pieter Abbeel
    In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022
  12. ICLR
    arXiv
    Efficient Empowerment Estimation for Unsupervised Stabilization
    Ruihan Zhao, Kevin Lu, Pieter Abbeel, and Stas Tiomkin
    In International Conference on Learning Representations (ICLR), 2021
  13. NeurIPS
    arXiv
    AvE: Assistance via Empowerment
    Yuqing Du, Stas Tiomkin, Emre Kiciman, Daniel Polani, Pieter Abbeel, and Anca Dragan
    In Advances in Neural Information Processing Systems (NeurIPS), 2020
  14. CDC
    IEEE
    Past-Future Information Bottleneck for Linear Feedback Systems
    Stas Tiomkin, Nadav Amir, and Naftali Tishby
    In 54th IEEE Conference on Decision and Control (CDC), 2015