Stas Tiomkin

6 papers · 2020–2025 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13)

Venues

AAAI (2) UAI (2) ICLR (1) NeurIPS (1)

Top co-authors

Jacob Adamczyk (4) Rahul V. Kulkarni (4) Argenis Arriojas (3) Pieter Abbeel (2) Volodymyr Makarenko (2) Kevin Lu (1) Yuqing Du (1) Daniel Polani (1) Ruihan Zhao (1) Anca Dragan (1)

Research topics

Machine Learning (4) Artificial Intelligence (3) Reinforcement Learning (3) Core AI (3) Optimization & Theory (3) Learning Types · Machine Learning (2) Methods (2) Deep Learning (1) Mathematics & Optimization (1) Applications (1) Learning Types · Deep Learning (1) Optimization (1)

Keywords

entropy regularization (3) reinforcement learning (3) optimal policy (2) reward shaping (2) value function (2) regret bound (1) sparse reward (1) variational lower bound (1) stochastic dynamics (1) soft value function (1) entropy-regularized reinforcement learning (1) shared autonomy (1) task composition (1) potential-based reward shaping (1) state-value function (1) compositional framework (1) gaussian channel (1) value function bound (1) zero-shot policy (1) empowerment estimation (1)

Papers

Bootstrapped Reward Shaping AAAI 2025 Bayesian inference approach for entropy regularized reinforcement learning with stochastic dynamics UAI 2023 Bounding the optimal value function in compositional reinforcement learning UAI 2023 Utilizing Prior Solutions for Reward Shaping and Composition in Entropy-Regularized Reinforcement Learning AAAI 2023 Efficient Empowerment Estimation for Unsupervised Stabilization ICLR 2021 AvE: Assistance via Empowerment NeurIPS 2020