Papers
7
Total Citations
135
H-Index
5
About
Luiz A. Celiberto is a leading researcher in artificial intelligence and robotics, whose work focuses on making reinforcement learning (RL) practical for real-world applications. His primary research areas include heuristic reinforcement learning, transfer learning, case-based reasoning, and control systems for autonomous robots. Celiberto’s major contribution lies in developing algorithms that accelerate RL by integrating prior knowledge—specifically, his pioneering work on transferring knowledge as heuristics using case-based reasoning. His most cited paper, "Transferring knowledge as heuristics in reinforcement learning: A case-based approach" (2015, 67 citations), established a framework that significantly improves learning efficiency. He further advanced this with the SARSA Accelerated by Transfer Learning (SATL) algorithm, demonstrated on real robots (2016). Celiberto has also applied his methods to RoboCup soccer agents, showcasing how heuristic acceleration enables faster learning in complex, dynamic environments. Beyond RL, his work extends to nonlinear predictive control for bipedal walkers and energy-efficient control for self-balancing vehicles, highlighting his versatility. With a career dedicated to bridging the gap between theoretical RL and practical deployment, Celiberto’s research continues to inspire students and researchers seeking to build smarter, more efficient autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Heuristic Reinforcement Learning Applied to RoboCup Simulation Agents25 citations · 2008
- 4
- 5
- 6
- 7