Amy McGovern
Papers
3
Total Citations
121
H-Index
3
About
Amy McGovern is a pioneering researcher whose work has fundamentally shaped the fields of reinforcement learning and artificial intelligence. Her key research areas include hierarchical reinforcement learning, macro-action discovery, and autonomous decision-making. McGovern’s major contributions center on analyzing and accelerating reinforcement learning through the use of temporally extended actions, or macro-actions. In her highly influential 1998 paper, "Roles of Macro-actions in Accelerating Reinforcement Learning" (67 citations), she provided the first rigorous analysis of the distinct advantages macro-actions offer, separating their benefits into improved exploration and more efficient learning. Her follow-up empirical analysis (43 citations) solidified these findings, while her 2001 work on discovering useful subgoals online (11 citations) demonstrated how autonomous agents could adapt to changing environments without pre-programmed knowledge. This subgoal discovery method has proven especially valuable for space robotics and other domains requiring adaptability. McGovern’s research has established foundational principles that continue to guide modern reinforcement learning approaches, making her work essential reading for anyone seeking to understand how agents can learn complex behaviors more efficiently through hierarchical structures.
Research Focus
Key Achievements
Top Papers
- 1Roles of Macro-actions in Accelerating Reinforcement Learning TITLE2:67 citations · 1998
- 2Macro-Actions in Reinforcement Learning: An Empirical Analysis43 citations · 1998
- 3Accelerating Reinforcement Learning through the Discovery of Useful Subgoals11 citations · 2001