Damien Ernst

About

Damien Ernst is a leading figure in reinforcement learning (RL) and optimal control, renowned for bridging the gap between theoretical dynamic programming and real-world applications. His seminal work, *Reinforcement Learning and Dynamic Programming Using Function Approximators* (2010, 933 citations), provides a foundational framework for scaling DP to complex, high-dimensional systems—from household appliances to advanced robotics—by integrating function approximation techniques. This contribution has become a cornerstone for researchers tackling decision-making in engineered systems with intricate dynamics. Ernst also authored the influential overview "Approximate Reinforcement Learning: An Overview" (2011, 65 citations), which synthesizes advances in approximation-based RL and highlights its successes across robotics, AI, and control. His innovative approach extends to planning under uncertainty, as seen in "Lazy Planning under Uncertainty by Optimizing Decisions on an Ensemble of Incomplete Disturbance Trees" (2008), which introduces efficient decision-making strategies for stochastic environments. With a career marked by high-impact citations and practical algorithmic breakthroughs, Ernst continues to shape how autonomous systems learn and adapt, inspiring students and researchers to push the boundaries of intelligent control.

Research Focus

Key Achievements

Top Papers

1. 1
   Reinforcement Learning and Dynamic Programming Using Function Approximators

   933 citations · 2010
2. 2
   Approximate reinforcement learning: An overview

   65 citations · 2011
3. 3
   Lazy Planning under Uncertainty by Optimizing Decisions on an Ensemble of Incomplete Disturbance Trees

   6 citations · 2008

Key Collaborators

Contact & Links