Alex Kearney
Papers
2
Total Citations
6
H-Index
2
About
Alex Kearney is an emerging researcher specializing in reinforcement learning, predictive knowledge architectures, and adaptive machine learning systems, with a particular focus on real-world robotics applications. Their work addresses one of the fundamental challenges in deploying intelligent systems in dynamic environments: how to learn and adapt continuously through direct interaction with the world, without costly offline retraining. Kearney's most notable contributions center on the development and evaluation of meta-learning strategies for predictive knowledge systems, particularly through the application of Temporal-Difference Incremental Delta-Bar-Delta (TIDBD) to sensor-rich robotic platforms. This research tackles the critical problem of step-size adaptation in online, incremental learning — a barrier that has historically limited the scalability of such systems in non-stationary, real-world settings. By examining how learning parameters can be automatically tuned rather than manually searched, Kearney's work moves the field meaningfully toward more autonomous and robust AI systems. Though still building their citation profile — with their leading work accumulating 4 citations — Kearney represents a growing voice in the intersection of temporal-difference learning and robotics. Students interested in online learning, continual adaptation, and embodied AI will find their research a valuable and practically grounded contribution to the field.
Research Focus
Key Achievements
Top Papers
- 1
- 2