Arsenii Mustafin
Scholar

Arsenii Mustafin

Google Scholar ID: sg4TPqYAAAAJ
PhD student, Boston University
Reinforcement LearningExplainable AI
Citations & Impact
All-time
Citations
27
 
H-index
2
 
i10-index
1
 
Publications
7
 
Co-authors
2
list available
Resume (English only)
Academic Achievements
  • 1. Paper 'MDP Geometry, Normalization and Reward Balancing Solvers' accepted to AISTATS 2025.
  • 2. Paper 'Analysis of Value Iteration Through Absolute Probability Sequences' under review, 2025.
  • 3. Paper 'Closing the Gap Between SVRG and TD-SVRG with Gradient Splitting' accepted to TMLR 2024.
Research Experience
  • 1. Worked on SemaFor DARPA project with BU team led by Prof. Kate Saenko.
  • 2. Participated in a project on Explainable AI with Prof. Sarah Adel Bargal.
  • 3. Visiting researcher at the University of Cyprus, presented MDP Geometry paper there.
Education
  • Degree: PhD; Institution: Boston University; Advisors: Prof. Alex Olshevsky, Prof. Yannis Paschalidis; Year: 6th year; Department: Computer Science.
Background
  • Research Interests: Reinforcement Learning (both theoretical and practical), other topics in Machine Learning including Computer Vision, Explainability, and Deep Fake Detection. Background: Completed PhD at Boston University and currently a postdoc at Aalto University.
Miscellany
  • Skills: Algorithmic - Reinforcement Learning, Deep Learning, classic Machine Learning algorithms, Time Series analysis; Software - PyTorch, Tensorflow (1&2), Linux (+git), SQL. Fluent in Mandarin, English, and native Russian.