About me
I am a fifth year PhD student in Applied Mathematics at York University, where I am fortunate to be supervised by Professor Hyejin Ku. My research focuses on risk-sensitive and distributional reinforcement learning. Previously, I worked as a quantitative researcher at Risklab AI, where I had the pleasure of collaborating with Professor Hamidreza Arian. I hold a BSc in Computer Science and an MBA in Finance from Sharif University of Technology. You can find my CV here.
I am generally interested in Reinforcement Learning and LLM Post-training. My main areas of research include:
- Risk-sensitive and Safe RL
- Knowledge distillation
Publications:
- Utility-Constrained Policy Optimization (NeurIPS 2026, arXiv, code)
- Decoupling Time and Risk: Risk-Sensitive Reinforcement Learning with General Discounting (NeurIPS 2026, arXiv, code)
- Risk-sensitive Actor-Critic with Static Spectral Risk Measures for Online and Offline Reinforcement Learning (Expert Systems with Applications, Journal, arXiv, code)
- Beyond CVaR: Leveraging Static Spectral Risk Measures for Enhanced Decision-Making in Distributional Reinforcement Learning (ICML 2025, PMLR, arXiv, code)
- Encoded Value-at-Risk: A Predictive Machine for Financial Risk Management (Mathematics and Computers in Simulation 2022, Journal, arXiv)
News
- September 2026: Our paper “Decoupling Time and Risk: Risk-Sensitive Reinforcement Learning with General Discounting” was accepted at NeurIPS 2026
- September 2026: Our paper “Utility-Constrained Policy Optimization” was accepted at NeurIPS 2026
- May 2026: I joined RBC Borealis as a research intern to work on Knowledge distillation
- May 2026: Preprint on “Utility-Constrained Policy Optimization”
- March 2026: Our paper “Risk-sensitive Actor-Critic with Static Spectral Risk Measures for Online and Offline Reinforcement Learning” was published in the Expert Systems with Applications journal
- February 2026: Preprint on “Decoupling Time and Risk: Risk-Sensitive Reinforcement Learning with General Discounting”
- July 2025: Preprint on “Risk-sensitive Actor-Critic with Static Spectral Risk Measures for Online and Offline Reinforcement Learning”
- May 2025: Our paper “Beyond CVaR: Leveraging Static Spectral Risk Measures for Enhanced Decision-Making in Distributional Reinforcement Learning” was accepted at ICML 2025
- January 2025: Preprint on “Beyond CVaR: Leveraging Static Spectral Risk Measures for Enhanced Decision-Making in Distributional Reinforcement Learning”
- December 2022: Our paper “Encoded Value-at-Risk: A Predictive Machine for Financial Risk Management” was published in the Mathematics and Computers in Simulation journal
- September 2021: Joined York University, Mathematics and Statistics department.
- November 2020: Preprint on “Encoded Value-at-Risk: A Predictive Machine for Financial Risk Management”
- January 2020: Public talk on “Building Diversified Portfolios that Outperform Out-of-Sample” (Link to Presentation in Farsi)
- September 2018: Received my bachelor’s degree in Computer Science, Ranked 1st in the class of 2018