Kernel Least-Squares Temporal Difference Learning

By Xin Xu, Tao Xie, Dewen Hu, Xicheng Lu. 2006

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Bo Dai
2. Sergey Levine
3. Qiang Liu
4. Nan Jiang
5. Arthur Gretton
6. Kenji Fukumizu
7. Krikamol Muandet
8. Bernhard Schölkopf

Citations in the corpus

• Modelling transition dynamics in MDPs with RKHS embeddings (2012, methodology): “Kernel methods have become increasingly popular in RL. Methods include kernel LSTD (Xu et al., 2005) and GPTD (Engel et al., 2005).”
• A Kernel Loss for Solving the Bellman Equation (2019, methodology): “In RL, authors have used kernels either to smooth the estimates of transition probabilities and rewards (Ormoneit & Sen, 2002), or to represent the value function (e.g., Xu et al., 2005, 2007; Taylor & Parr, 2009).”
• Policy evaluation with temporal differences: a survey and comparison (2015, methodology): “GPTD (Engel et al., 2003) and LSTD (Xu et al., 2005, known as Kernelized LSTD, KLSTD) have been extended to use kernelized value functions.”