Montaser Mohammedalamen, PhD

Publications

Peer-Reviewed Journal Articles

1. Montaser Mohammedalamen, Dustin Morrill, Alexander Sieusahai, Yash Satsangi, and Michael Bowling, "Learning to Be Cautious," Transactions on Machine Learning Research (TMLR), 2025.
   paper | code | bibtex | talk

Refereed Conference Publications

1. Montaser Mohammedalamen and Michael Bowling, "Generalization in Monitored Markov Decision Processes (Mon-MDPs)," Reinforcement Learning Conference (RLC), Montreal, Canada, 2026.
   arXiv | code | bibtex | talk
2. Simone Parisi, Montaser Mohammedalamen, Alireza Kazemipour, Matthew E. Taylor, and Michael Bowling, "Monitored Markov Decision Processes," International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Auckland, New Zealand, 2024.
   paper | code | bibtex | talk

Workshop Papers & Preprints

1. Montaser Mohammedalamen, K. Roice, R. McLean, A. Lefaivre Škopac, "A Systematic Investigation of The RL-Jailbreaker in LLMs," Agents in the Wild: Safety, Security, and Beyond Workshop, ICML, 2026.
   arXiv
2. R. McLean, T. E. Lee, Montaser Mohammedalamen, K. Roice, G. Berseth, P. M. Pilarski, M. C. Machado, A. Lefaivre Škopac, B. Rosman, "AI Agent Safety is a Reinforcement Learning Problem," Agents in the Wild: Safety, Security, and Beyond Workshop, ICML, 2026.
   paper
3. Montaser Mohammedalamen, Michael Bowling, and Matthew E. Taylor, "Learning To Be Cautious for Industrial Chemical Control," Under review.
4. D. Khamies, Montaser Mohammedalamen, and B. Rosman, "Transfer Learning for Prosthetics Using Imitation Learning," Black in AI Workshop, NeurIPS, 2018.
   arXiv | code | bibtex

Theses

1. Montaser Mohammedalamen, "Reinforcement Learning with Partially Observable Rewards," PhD Thesis, University of Alberta, 2026.
   thesis
2. Montaser Mohammedalamen, "Learning Actions Representation In Reinforcement Learning for Safe Exploration," Master's Thesis, 2019.