Payam Mousavi
Papers
1
Total Citations
131
H-Index
1
About
Payam Mousavi is a leading researcher at the intersection of artificial intelligence and human-centered computing, with a primary focus on reinforcement learning (RL) and human-in-the-loop (HITL) systems. His most influential work, the 2024 survey “Human-in-the-Loop Reinforcement Learning: A Survey and Position on Requirements, Challenges, and Opportunities,” has already garnered 131 citations, establishing him as a key voice in shaping how autonomous agents learn with human guidance. Mousavi’s major contribution lies in reframing RL as fundamentally a HITL paradigm—arguing that even fully autonomous agents originate from and depend on human interaction, oversight, and feedback. This perspective has profound implications for designing safer, more transparent, and ethically aligned AI systems. His work systematically maps the requirements and challenges of integrating human input into RL loops, from reward design to safety constraints, offering a roadmap for future research. By bridging technical rigor with human factors, Mousavi’s research is essential reading for anyone developing AI that must operate alongside people. His contributions are driving a critical shift toward more collaborative, responsible AI development.
Research Focus
Key Achievements
Top Papers
- 1