2012
NeurIPS
NeurIPS 2012
Non-parametric Approximate Dynamic Programming via the Kernel Method
Abstract
This paper presents a novel non-parametric approximate dynamic programming (ADP) algorithm that enjoys graceful, dimension-independent approximation and sample complexity guarantees. In particular, we establish both theoretically and computationally that our proposal can serve as a viable alternative to state-of-the-art parametric ADP algorithms, freeing the designer from carefully specifying an approximation architecture. We accomplish this by developing a kernel-based mathematical program for ADP. Via a computational study on a controlled queueing network, we show that our non-parametric procedure is competitive with parametric ADP approaches.
🌉
Interdisciplinary Bridge
- Artificial Intelligence and Mathematics & Optimization and Reinforcement Learning
📈
Trend Setter
- Markov Decision Process
🐣
Hot Topic Early Bird
- sample complexity
Authors
Topics
Machine Learning > Optimization & Theory > Learning Theory
Machine Learning > Optimization & Theory > Optimization
Reinforcement Learning > Methods > Deep RL
Mathematics & Optimization > Optimization > Continuous Optimization
Mathematics & Optimization > Optimization > Stochastic Methods
Machine Learning > Core Methods > Kernel Methods
Artificial Intelligence > Core AI > Decision Making
Machine Learning > Learning Types > Markov Decision Process