Evan Dallas
Papers
2
Total Citations
6
H-Index
1
About
Evan Dallas is a pioneering researcher at the intersection of social robotics, human-robot interaction, and AI-driven education. His work focuses on developing sample-efficient learning methods and exploring how robots can replicate high-quality human teaching practices. Dallas’s most cited paper, “A Sample Efficiency Improved Method via Hierarchical Reinforcement Learning Networks” (2022, 5 citations), introduces a novel approach to learning from demonstration (LfD) that significantly reduces the number of demonstrations required for robots to acquire complex tasks—a critical advancement for deploying social robots in real-world healthcare, educational, and service settings. His more recent study, “Exploring Task-Level Contingent Mediations for Vocabulary Instruction across Robot, Virtual, and Human Teachers” (2024, 1 citation), investigates how robots can emulate contingent mediation strategies—a hallmark of effective human teaching—to improve vocabulary learning outcomes. By bridging hierarchical reinforcement learning with pedagogical theory, Dallas is shaping the next generation of adaptive, socially intelligent robots capable of personalized instruction. His work not only advances technical efficiency in robot learning but also deepens our understanding of how machines can meaningfully support human development.
Research Focus
Key Achievements
Top Papers
- 1
- 2