Professor of Computer Science
I study how intelligent agents learn, coordinate, and make accountable decisions in complex environments. My work connects multi-agent systems, reinforcement learning, and networked organizations with applications in logistics, robotics, and cyber-physical systems.
Learning and coordination — Multi-agent reinforcement learning, constrained control, and digital twins.
Decision-making foundations — Perspective-aware cognition, networked organizations, and resource allocation.
Trustworthy AI — Accountability, runtime safeguards, fairness, and cyber resilience.
Research frameworks and experiment pipelines, with direct links to code and publications.
|
Sustainable multi-agent coordination Hierarchical reinforcement learning for maritime logistics, combining emissions budgets with fairness-aware resource allocation. |
Latency-aware resource allocation An auction mechanism and experiment pipeline for resource allocation across heterogeneous-delay communication networks. |
|
Learning-based industrial control A multi-agent digital-twin testbed for scheduling and residual control of the Tennessee Eastman Process, with a solver-backed safety shield. |
Perspective-aware cognition A formal framework for representing, propagating, and reconciling agents’ beliefs across different observers and situations. |
|
Adaptation for heterogeneous robots Reward-only sensor adaptation for robot teams: adapt compact observation transforms while keeping the shared policy frozen. |
Cyber resilience and communication A framework coupling cyber-incident response and verified communication under misinformation. |
Explore all public repositories →
I lead CHMARL, an applied AI project developing decision support for port and logistics coordination. The work connects multi-agent reinforcement learning with operational constraints, sustainability, and fair resource allocation.
Project website · Original CH-MARL framework · EcoFair research code
I welcome research and industry collaboration on multi-agent learning, trustworthy decision systems, and applied AI.
Contact: alqithami@gmail.com
For experiment setup, scope, and citation details, consult each repository’s README. Archived repositories preserve fixed research artifacts.