Non-parametric Approximate Dynamic Programming via the Kernel Method

2012-12-01 · NeurIPS 2012 12 · Nikhil Bhat, Vivek Farias, Ciamac C. Moallemi

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Safe Approximate Dynamic Programming Via Kernelized Lipschitz Estimation

2019-07-03 · Ankush Chakrabarty, Devesh K. Jha, Gregery T. Buzzard, Yebin Wang 외

We develop a method for obtaining safe initial policies for reinforcement learning via approximate dynamic programming (ADP) techniques for uncertain systems evolving with discrete-time dynamics. We employ kernelized Lip…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

A Non-Parametric Approach to Dynamic Programming

2011-12-01 · NeurIPS 2011 12 · Oliver B. Kroemer, Jan R. Peters

In this paper, we consider the problem of policy evaluation for continuous-state systems. We present a non-parametric approach to policy evaluation, which uses kernel density estimation to represent the system. The true …

Density Estimation

Approximate Dynamic Programming based Model Predictive Control of Nonlinear systems

2023-12-10 · Keerthi Chacko, Midhun T. Augustine, S. Janardhanan, Deepak U. Patil 외

This paper studies the optimal control problem for discrete-time nonlinear systems and an approximate dynamic programming-based Model Predictive Control (MPC) scheme is proposed for minimizing a quadratic performance mea…

Model Predictive Control

SOCKS: A Stochastic Optimal Control and Reachability Toolbox Using Kernel Methods

2022-03-12 · Adam J. Thorpe, Meeko M. K. Oishi

We present SOCKS, a data-driven stochastic optimal control toolbox based in kernel methods. SOCKS is a collection of data-driven algorithms that compute approximate solutions to stochastic optimal control problems with a…

Learning Efficient Representations for Reinforcement Learning

2015-08-28 · Yanping Huang

Markov decision processes (MDPs) are a well studied framework for solving sequential decision making problems under uncertainty. Exact methods for solving MDPs based on dynamic programming such as policy iteration and va…

Decision Making reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1