Off-Policy Temporal Difference Learning with Function Approximation
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Learning from Scarce Experience
ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning
Eligibility Traces for Off-Policy Policy Evaluation
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Policy Improvement for POMDPs Using Normalized Importance Sampling
UAI '01 Proceedings of the 17th Conference in Uncertainty in Artificial Intelligence
Least-squares policy iteration
The Journal of Machine Learning Research
Reinforcement learning by reward-weighted regression for operational space control
Proceedings of the 24th international conference on Machine learning
Covariate Shift Adaptation by Importance Weighted Cross Validation
The Journal of Machine Learning Research
An approach to fuzzy control of nonlinear systems: stability and design issues
IEEE Transactions on Fuzzy Systems
Density Ratio Estimation: A New Versatile Tool for Machine Learning
ACML '09 Proceedings of the 1st Asian Conference on Machine Learning: Advances in Machine Learning
Least absolute policy iteration for robust value function approximation
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Semi-supervised speaker identification under covariate shift
Signal Processing
Neural Networks
Hi-index | 0.00 |
Off-policy reinforcement learning is aimed at efficiently using data samples gathered from a policy that is different from the currently optimized policy. A common approach is to use importance sampling techniques for compensating for the bias of value function estimators caused by the difference between the data-sampling policy and the target policy. However, existing off-policy methods often do not take the variance of the value function estimators explicitly into account and therefore their performance tends to be unstable. To cope with this problem, we propose using an adaptive importance sampling technique which allows us to actively control the trade-off between bias and variance. We further provide a method for optimally determining the trade-off parameter based on a variant of cross-validation. We demonstrate the usefulness of the proposed approach through simulations.