Alessio Russo

About Me

I am a researcher in Reinforcement Learning and Control methodology. Currently a Postdoc at Boston University, where I’m advised by Prof. Pacchiano Aldo.

• I have a Ph.D. in Electrical Engineering from KTH Royal Insitute of Technology (Stockholm), where I was supervised by Prof. Proutiere Alexandre at the Division of Decision and Control Systems.
• Due to my past experiences, and interests, I have a versatile background, with both theoretical and practical expertise.
• Programming languages: Python, C, C++

Research Interests

My research interests are in statistical learning, particularly in the areas of learning for sequential decision making.

• Reinforcement Learning: adaptive/pure exploration (theoretical and practical), self-play RL, robust/adversarial RL and bandit algorithms.
• Adaptive and Robust Control: adaptive control (e.g., MRAC/L1), adaptive MPC and non-linear control.

News

• [Sept. 2025] “Adversarial Diffusion for Robust Reinforcement Learning” has been accepted as a poster to NeurIPS 2025 (San Diego, USA)
• [Sept. 2025] “In-Context Pure Exploration” has been accepted to the NY-RL workshop @ NY-RL 2025 (New York, USA)
• [Jun. 2025] “In-Context Pure Exploration” has been accepted to the EXAIT workshop @ ICML 2025 (Vancouver, Canada)
• [Jun. 2025] Presenting “Optimal Exploration With Feedback Graphs” at Informs APS 2025, in Atlanta.
• [Apr. 2025] “Adaptive Exploration for Multi-Reward Multi-Policy Exploration” has been accepted as a poster to ICML 2025 (Vancouver, Canada)
• [Dec. 2024] Our paper “Pure Exploration with Feedback Graphs” has been accepted as an oral to AISTATS 2025 (Phuket, Thailand)
• [Sep. 2024] “Multi-Reward Best-Policy Identification” has been accepted as a poster to NeurIPS 2024 (Vancouver, Canada)
• [Jul. 2024] Our paper about “Fair Best Arm Identification with Fixed Confidence” has been accepted sa an oral to CDC 2024 (Milan, Italy)

Recent Publications (and preprints)

Powered by Jekyll and Minimal Light theme.