View Profile

Daniil Tiapkin

None · HSE University

https://researchid.co/dtiapkin
@hse.ru
407Google Scholar Citations
11Google Scholar h-index
13Google Scholar i10-index

Research Interests

Reinforcement learning, stochastic optimization

Education

MSc in Computer Science 2021-2023: HSE University, specialization: Math of Machine Learning BSc in Computer Science 2017-2021: HSE Unversity, specialization: Theoretical Computer Science

Recent Google Scholar Publications

  1. Learning Shortest Paths with Generative Flow Networks
    arXiv preprint arXiv:2603.01786 , 2026, 2026 | Citations: 1.0
  2. Beyond Softmax and Entropy: Convergence Rates of Policy Gradients with -SoftArgmax Parameterization Coupled Regularization
    The Fourteenth International Conference on Learning Representations , 2026, 2026 | Citations: 1.0
  3. On Global Convergence Rates for Federated Softmax Policy Gradient under Heterogeneous Environments
    The 29th International Conference on Artificial Intelligence and Statistics , 2026, 2026 | Citations: 5.0
  4. gfnx: Fast and Scalable Library for Generative Flow Networks in JAX
    arXiv preprint arXiv:2511.16592 , 2025, 2025 | Citations: 2.0
  5. Sample-Efficient Reinforcement Learning: Exploration, Imitation, and Online Learning
    Institut polytechnique de Paris , 2025, 2025

Links