Papers
11
Total Citations
261
H-Index
7
About
Marc Schoenauer is a pioneering figure in evolutionary computation and reinforcement learning, whose work bridges the gap between machine learning and robotics. His key research areas include evolutionary algorithms, preference-based reinforcement learning, and evolutionary robotics. Schoenauer's most significant contribution is the development of APRIL (Active Preference Learning-Based Reinforcement Learning), a groundbreaking framework that enables robots to learn from human preferences rather than explicit reward functions—a critical advance for domains like swarm robotics where expert demonstrations are impractical. This work, along with his Preference-Based Policy Learning approach (83 citations), has fundamentally changed how machines can acquire complex behaviors through minimal human feedback. His research on open-ended evolutionary robotics, using information-theoretic approaches to foster emergent behaviors, has been highly influential in the field. With over 94 citations for his APRIL paper alone, Schoenauer's work continues to shape modern reinforcement learning. His notable achievements include pioneering the use of Voronoi-based fuzzy controllers in evolutionary systems and advancing interactive robot education through Bayesian policy search methods.
Research Focus
Key Achievements
Top Papers
- 1APRIL: Active Preference Learning-Based Reinforcement Learning94 citations · 2012
- 2Preference-Based Policy Learning83 citations · 2011
- 3Artificial Evolution25 citations · 2004
- 4Open-Ended Evolutionary Robotics: An Information Theoretic Approach11 citations · 2010
- 5Evolution of Voronoi-Based Fuzzy Controllers10 citations · 2004
- 6APRIL: Active Preference-learning based Reinforcement Learning10 citations · 2012
- 7Interactive Robot Education9 citations · 2013
- 8Evolving Symbolic Controllers6 citations · 2003
- 9Evolution of Voronoi based fuzzy recurrent controllers5 citations · 2005
- 10