Model-based policy gradients with parameter-based exploration by least-squares conditional density estimation
- 1 September 2014
- journal article
- Published by Elsevier in Neural Networks
- Vol. 57, 128-140
Abstract
No abstract availableKeywords
All Related Versions
This publication has 22 references indexed in Scilit:
- Sufficient Dimension Reduction via Squared-Loss Mutual Information EstimationNeural Computation, 2013
- Density-ratio matching under the Bregman divergence: a unified framework of density-ratio estimationAnnals of the Institute of Statistical Mathematics, 2011
- A Survey on Policy Search for RoboticsFoundations and Trends in Robotics, 2011
- Efficient exploration through active learning for value function approximation in reinforcement learningNeural Networks, 2010
- Parameter-exploring policy gradientsNeural Networks, 2010
- Least Absolute Policy Iteration-A Robust Approach to Value Function ApproximationIEICE Transactions on Information and Systems, 2010
- Least-Squares Conditional Density EstimationIEICE Transactions on Information and Systems, 2010
- Adaptive importance sampling for value function approximation in off-policy reinforcement learningNeural Networks, 2009
- Geodesic Gaussian kernels for value function approximationAutonomous Robots, 2008
- Using Expectation-Maximization for Reinforcement LearningNeural Computation, 1997