Abeer Dyoub
Papers
1
Total Citations
4
H-Index
1
About
Abeer Dyoub’s research lies at the intersection of artificial intelligence, robotics, and constraint-based reasoning, with a particular focus on deep reinforcement learning (RL) and procedural environment generation. Her most cited work, “Extension of constraint-procedural logic-generated environments for deep Q-learning agent training and benchmarking” (2023, 4 citations), introduces a novel framework that leverages constraint-procedural logic to create diverse, scalable training environments for autonomous robots. This contribution addresses a critical bottleneck in RL: the need for rich, reproducible benchmarks to evaluate agent performance in tasks like exploration and object collection. By integrating logical constraints into procedural generation, Dyoub enables more systematic testing of deep Q-learning agents, bridging the gap between symbolic AI and data-driven methods. Her work is particularly notable for its practical implications in robotics, where robust training environments are essential for real-world deployment. Though early in her career, Dyoub’s innovative approach to combining logic programming with reinforcement learning has already garnered attention, positioning her as a promising voice in the quest for more intelligent, adaptable autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1