Stas Tiomkin

Publication Activity (10 Years)

Years Active: 2008-2024
Publications (10 Years): 27

Top Topics

Markov Decision Process

Maximum Entropy

Dynamical Systems

Reinforcement Learning

Top Venues

Publications

Nadav Amir, Stas Tiomkin, Angela Langdon
Learning telic-controllable state representations. CoRR (2024)
Jacob Adamczyk, Volodymyr Makarenko, Stas Tiomkin, Rahul V. Kulkarni
Boosting Soft Q-Learning by Bounding. CoRR (2024)
Suruchi Sharma, Volodymyr Makarenko, Gautam Kumar, Stas Tiomkin
Controllability-Constrained Deep Network Models for Enhanced Control of Dynamical Systems. CoRR (2023)
Stas Tiomkin, Ilya Nemenman, Daniel Polani, Naftali Tishby
Intrinsic Motivation in Dynamical Control Systems. CoRR (2023)
Jacob Adamczyk, Volodymyr Makarenko, Argenis Arriojas, Stas Tiomkin, Rahul V. Kulkarni
Bounding the optimal value function in compositional reinforcement learning. UAI (2023)
Tristan Shah, Feruza Amirkulova, Stas Tiomkin
Taming Waves: A Physically-Interpretable Machine Learning Framework for Realizable Control of Wave Dynamics. CoRR (2023)
Jacob Adamczyk, Volodymyr Makarenko, Argenis Arriojas, Stas Tiomkin, Rahul V. Kulkarni
Bounding the Optimal Value Function in Compositional Reinforcement Learning. CoRR (2023)
Wooyoung Chung, Daniel Polani, Stas Tiomkin
Dimensionality Reduction of Dynamics on Lie Manifolds via Structure-Aware Canonical Correlation Analysis. CoRR (2023)
Argenis Arriojas, Jacob Adamczyk, Stas Tiomkin, Rahul V. Kulkarni
Bayesian inference approach for entropy regularized reinforcement learning with stochastic dynamics. UAI (2023)
Jacob Adamczyk, Stas Tiomkin, Rahul V. Kulkarni
Compositionality and Bounds for Optimal Value Functions in Reinforcement Learning. CoRR (2023)
Derek Lilienthal, Paul Mello, Magdalini Eirinaki, Stas Tiomkin
Multi-Resolution Diffusion for Privacy-Sensitive Recommender Systems. CoRR (2023)
Jacob Adamczyk, Argenis Arriojas, Stas Tiomkin, Rahul V. Kulkarni
Utilizing Prior Solutions for Reward Shaping and Composition in Entropy-Regularized Reinforcement Learning. AAAI (2023)
Jacob Adamczyk, Argenis Arriojas, Stas Tiomkin, Rahul V. Kulkarni
Utilizing Prior Solutions for Reward Shaping and Composition in Entropy-Regularized Reinforcement Learning. CoRR (2022)
Kyle Hollins Wray, Stas Tiomkin, Mykel J. Kochenderfer, Pieter Abbeel
Multi-Objective Policy Gradients with Topological Constraints. IROS (2022)
Kyle Hollins Wray, Stas Tiomkin, Mykel J. Kochenderfer, Pieter Abbeel
Multi-Objective Policy Gradients with Topological Constraints. CoRR (2022)
Philippe Hansen-Estruch, Wenling Shang, Lerrel Pinto, Pieter Abbeel, Stas Tiomkin
GEM: Group Enhanced Model for Learning Dynamical Control Systems. CoRR (2021)
Ruihan Zhao, Kevin Lu, Pieter Abbeel, Stas Tiomkin
Efficient Empowerment Estimation for Unsupervised Stabilization. ICLR (2021)
Argenis Arriojas, Stas Tiomkin, Rahul V. Kulkarni
Closed-Form Analytical Results for Maximum Entropy Reinforcement Learning. CoRR (2021)
Yuqing Du, Stas Tiomkin, Emre Kiciman, Daniel Polani, Pieter Abbeel, Anca D. Dragan
AvE: Assistance via Empowerment. NeurIPS (2020)
Yuqing Du, Stas Tiomkin, Emre Kiciman, Daniel Polani, Pieter Abbeel, Anca D. Dragan
AvE: Assistance via Empowerment. CoRR (2020)
Albert Zhan, Stas Tiomkin, Pieter Abbeel
Preventing Imitation Learning with Adversarial Policy Ensembles. CoRR (2020)
Xingyu Lu, Kimin Lee, Pieter Abbeel, Stas Tiomkin
Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learning. CoRR (2020)
Ruihan Zhao, Pieter Abbeel, Stas Tiomkin
Efficient Online Estimation of Empowerment for Reinforcement Learning. CoRR (2020)
Xingyu Lu, Stas Tiomkin, Pieter Abbeel
Predictive Coding for Boosting Deep Reinforcement Learning with Sparse Rewards. CoRR (2019)
Ruihan Zhao, Stas Tiomkin, Pieter Abbeel
Learning Efficient Representation for Intrinsic Motivation. CoRR (2019)
Stas Tiomkin, Daniel Polani, Naftali Tishby
Control Capacity of Partially Observable Dynamic Systems in Continuous Time. CoRR (2017)
Stas Tiomkin, Naftali Tishby
A Unified Bellman Equation for Causal Information and Value in Markov Decision Processes. CoRR (2017)
Nadav Amir, Stas Tiomkin, Naftali Tishby
Past-future Information Bottleneck for linear feedback systems. CDC (2015)
Ron M. Hecht, Aharon Bar-Hillel, Stas Tiomkin, Hadar Levi, Omer Tsimhoni, Naftali Tishby
Cognitive workload and vocabulary sparseness: theory and practice. INTERSPEECH (2015)
Stas Tiomkin, David Malah, Slava Shechtman, Zvi Kons
A Hybrid Text-to-Speech System That Combines Concatenative and Statistical Synthesis Units. IEEE Trans. Speech Audio Process. 19 (5) (2011)
Stas Tiomkin, David Malah, Slava Shechtman
Statistical Text-to-Speech Synthesis Based on Segment-Wise Representation With a Norm Constraint. IEEE Trans. Speech Audio Process. 18 (5) (2010)
Stas Tiomkin, David Malah
Statistical text-to-speech synthesis with improved dynamics. INTERSPEECH (2008)