Peter Sunehag
Papers
1
Total Citations
6
H-Index
1
About
Peter Sunehag is a researcher in artificial intelligence and machine learning, with a primary focus on reinforcement learning, multi-agent systems, and sparse kernel methods. His work bridges theoretical foundations and practical algorithms, most notably through the development of Sparse Kernel-SARSA(λ) with an Eligibility Trace, a method that enhances sample efficiency and computational tractability in reinforcement learning by combining kernel-based function approximation with eligibility traces. This contribution, published in 2011, has garnered 6 citations and remains a reference for researchers exploring scalable, non-parametric approaches to sequential decision-making. Sunehag’s broader impact is evident in his collaborative work on multi-agent reinforcement learning, where he has contributed to frameworks for cooperative and competitive AI systems. His research is characterized by a commitment to algorithmic elegance and real-world applicability, making his work valuable for students and practitioners seeking to understand the intersection of kernel methods and reinforcement learning. Through his publications, Sunehag has helped advance the efficiency and robustness of learning algorithms, solidifying his role as a thoughtful contributor to the machine learning community.
Research Focus
Key Achievements
Top Papers
- 1Sparse Kernel-SARSA(λ) with an Eligibility Trace6 citations · 2011