amidimohsen
Mohsen Amidzadeh
Postdoctoral Researcher | Reinforcement Learning, Stochastic Control & Probabilistic Methods
About Me
I am a postdoctoral researcher with over nine years of experience in academic research. My work focuses on developing new models and theory at the intersection of reinforcement learning and stochastic control, particularly for problems involving forward-backward dynamics.
I earned my PhD from Aalto University, where my research centered on edge caching in wireless networks using stochastic geometry. Before that, I completed my Master's degree at Sharif University of Technology, focusing on robust object tracking with particle filters.
I am passionate about tackling challenges that demand a strong mathematical foundation in areas like stochastic optimization, optimal control, signal processing, and estimation theory.
If you are interested in any of my research interest through my ongoing projects, do not hesitate and contact me for a possible collaboration .
News
- July'26 » Our paper on "Non-Parametric Optimization for Scalable Learning in Stochastic Decision Problems" was accepted to ICML: International Conference on Machine Learning.
- March'26 » Our paper on "Malliavin-based Gradient Projection Algorithm" is now available: refer to Projects.
- Dec'25 » Our paper on "Cache-aided Streaming via Forward-Backward Reinforcement Learning" is now available: refer to Projects.
- July'25 » Our paper on "Forward-Backward Reinforcement Learning" was accepted to TMLR: Transactions on Machine Learning Research .
- May'24 » I will be presenting two single-authored papers related to Multi-Objective Reinforcement Learning and Time-Varying Optimization at the IEEE Conference on Decision and Control (CDC).
- Jan'24 » I defended my PhD thesis and officially started my postdoctoral position focusing on reinforcement learning theory.
Research Interests
- Reinforcement Learning (Theory and Algorithms)
- Stochastic Control and Optimization
- Stochastic Geometry and its Applications in Wireless Networks
- Estimation Theory and Signal Processing