Error Bounds for Approximations from Projected Linear Equations

We consider linear fixed point equations and their approximations by projection on a low dimensional subspace. We derive new bounds on the approximation error of the solution, which are expressed in terms of low dimensional matrices and can be computed by simulation. When the fixed point mapping is a contraction, as is typically the case in Markov decision processes (MDP), one of our bounds is always sharper than the standard contraction-based bounds, and another one is often sharper. The former bound is also tight in a worst-case sense. Our bounds also apply to the noncontraction case, including policy evaluation in MDP with nonstandard projections that enhance exploration. There are no error bounds currently available for this case to our knowledge.

[1]  Dimitri P. Bertsekas,et al.  Dynamic Programming and Optimal Control, Vol. II , 1976 .

[2]  Charles R. Johnson,et al.  Matrix analysis , 1985, Statistical Inference for Engineers and Data Scientists.

[3]  Dimitri P. Bertsekas,et al.  A Counterexample to Temporal Differences Learning , 1995, Neural Computation.

[4]  Dimitri P. Bertsekas,et al.  Dynamic Programming and Optimal Control, Two Volume Set , 1995 .

[5]  John N. Tsitsiklis,et al.  Neuro-Dynamic Programming , 1996, Encyclopedia of Machine Learning.

[6]  John N. Tsitsiklis,et al.  Analysis of Temporal-Diffference Learning with Function Approximation , 1996, NIPS.

[7]  Guanrong Chen,et al.  Approximate Solutions of Operator Equations , 1997 .

[8]  Andrew G. Barto,et al.  Reinforcement learning , 1998 .

[9]  Richard S. Sutton,et al.  Introduction to Reinforcement Learning , 1998 .

[10]  John N. Tsitsiklis,et al.  Average cost temporal-difference learning , 1997, Proceedings of the 36th IEEE Conference on Decision and Control.

[11]  John N. Tsitsiklis,et al.  Optimal stopping of Markov processes: Hilbert space theory, approximation algorithms, and an application to pricing high-dimensional financial derivatives , 1999, IEEE Trans. Autom. Control..

[12]  Justin A. Boyan,et al.  Least-Squares Temporal Difference Learning , 1999, ICML.

[13]  John N. Tsitsiklis,et al.  Actor-Critic Algorithms , 1999, NIPS.

[14]  Rémi Munos,et al.  Error Bounds for Approximate Policy Iteration , 2003, ICML.

[15]  Dimitri P. Bertsekas,et al.  Least Squares Policy Evaluation Algorithms with Linear Function Approximation , 2003, Discret. Event Dyn. Syst..

[16]  Vijay R. Konda,et al.  OnActor-Critic Algorithms , 2003, SIAM J. Control. Optim..

[17]  Steven J. Bradtke,et al.  Linear Least-Squares algorithms for temporal difference learning , 2004, Machine Learning.

[18]  Richard S. Sutton,et al.  Learning to predict by the methods of temporal differences , 1988, Machine Learning.

[19]  Daniel B. Szyld,et al.  The many proofs of an identity on the norm of oblique projections , 2006, Numerical Algorithms.

[20]  David Choi,et al.  A Generalized Kalman Filter for Fixed Point Approximation and Efficient Temporal-Difference Learning , 2001, Discret. Event Dyn. Syst..

[21]  D. Bertsekas,et al.  A Least Squares Q-Learning Algorithm for Optimal Stopping Problems , 2007 .

[22]  D. Bertsekas,et al.  Q-learning algorithms for optimal stopping based on least squares , 2007, 2007 European Control Conference (ECC).

[23]  D. Bertsekas,et al.  Journal of Computational and Applied Mathematics Projected Equation Methods for Approximate Solution of Large Linear Systems , 2022 .

[24]  Benjamin Van Roy.  On Regression-Based Stopping Times , 2010, Discret. Event Dyn. Syst..