Matrix analysis
A counterexample to temporal differences learning
Neural Computation
Linear least-squares algorithms for temporal difference learning
Machine Learning - Special issue on reinforcement learning
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Neuro-Dynamic Programming
Least Squares Policy Evaluation Algorithms with Linear Function Approximation
Discrete Event Dynamic Systems
Learning to Predict by the Methods of Temporal Differences
Machine Learning
Least-Squares Temporal Difference Learning
ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
SIAM Journal on Control and Optimization
A Generalized Kalman Filter for Fixed Point Approximation and Efficient Temporal-Difference Learning
Discrete Event Dynamic Systems
Dynamic Programming and Optimal Control, Vol. II
Dynamic Programming and Optimal Control, Vol. II
Projected equation methods for approximate solution of large linear systems
Journal of Computational and Applied Mathematics
On Regression-Based Stopping Times
Discrete Event Dynamic Systems
Brief paper: Average cost temporal-difference learning
Automatica (Journal of IFAC)
Finite-sample analysis of least-squares policy iteration
The Journal of Machine Learning Research
Hi-index | 0.00 |
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.