Corpus ID: 9573489

Online Linear Regression and Its Application to Model-Based Reinforcement Learning

@inproceedings{Strehl2007OnlineLR,
  title={Online Linear Regression and Its Application to Model-Based Reinforcement Learning},
  author={A. Strehl and M. Littman},
  booktitle={NIPS},
  year={2007}
}
We provide a provably efficient algorithm for learning Markov Decision Processes (MDPs) with continuous state and action spaces in the online setting. Specifically, we take a model-based approach and show that a special type of online linear regression allows us to learn MDPs with (possibly kernalized) linearly parameterized dynamics. This result builds on Kearns and Singh's work that provides a provably efficient algorithm for finite state MDPs. Our approach is not restricted to the linear… Expand
Exploring compact reinforcement-learning representations with linear regression
Model Selection in Reinforcement Learning
Online Feature Selection for Model-based Reinforcement Learning
Efficient Value-Function Approximation via Online Linear Regression
Reinforcement Learning Algorithms for MDPs
Reinforcement Learning in Finite MDPs: PAC Analysis
Cover tree Bayesian reinforcement learning
Feature Selection for Model-based Reinforcement Learning
Online exploration in least-squares policy iteration
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 17 REFERENCES
Near-Optimal Reinforcement Learning in Polynomial Time
Exploration and apprenticeship learning in reinforcement learning
R-MAX - A General Polynomial Time Algorithm for Near-Optimal Reinforcement Learning
On the sample complexity of reinforcement learning.
Exploration in Metric State Spaces
PAC adaptive control of linear systems
A Sparse Sampling Algorithm for Near-Optimal Planning in Large Markov Decision Processes
Introduction to Reinforcement Learning
Reinforcement Learning: An Introduction
TD-Gammon, a Self-Teaching Backgammon Program, Achieves Master-Level Play
...
1
2
...