David Abel

Papers

Total Citations

H-Index

About

David Abel is a leading researcher in artificial intelligence, with a primary focus on reinforcement learning, AI safety, and the intersection of machine learning with human values. His most influential work, "Goal-Based Action Priors" (2015), introduced a novel framework enabling robots to efficiently prune irrelevant actions in large, stochastic state spaces by leveraging goal- and state-dependent priors—a foundational contribution that has garnered 23 citations and advanced the practical deployment of interactive AI systems. Abel’s broader research explores how to build agents that not only achieve complex objectives but also align with human intent, addressing critical challenges in AI alignment and value learning. His work is widely recognized for bridging theoretical rigor with real-world applicability, making him a key voice in discussions on safe and beneficial AI. With a growing citation impact and a reputation for innovative problem-solving, Abel continues to shape the future of autonomous decision-making, inspiring students and researchers to consider both the technical and ethical dimensions of intelligent systems.