Reinforcement learning of motor skills with policy gradients
Authors:
- Jan PetersJPJan Peters
- Stefan SchaalSSStefan Schaal
Top Cited Papers
- 1 May 2008
- journal article
- Published by Elsevier in Neural Networks
- Vol. 21 (4) , 682-697
Abstract
No abstract availableKeywords
This publication has 27 references indexed in Scilit:
- Minimum Acceleration Criterion with Constraints Implies Bang-Bang Control as an Underlying Principle for Optimal Trajectories of Arm Reaching MovementsNeural Computation, 2008
- Motor primitives in vertebrates and invertebratesCurrent Opinion in Neurobiology, 2005
- Real-time learning: a ball on a beam2003
- Feature Article: Optimization for simulation: Theory vs. PracticeINFORMS Journal on Computing, 2002
- Infinite-Horizon Policy-Gradient EstimationJournal of Artificial Intelligence Research, 2001
- Experiments with Infinite-Horizon, Policy-Gradient EstimationJournal of Artificial Intelligence Research, 2001
- Natural Gradient Works Efficiently in LearningNeural Computation, 1998
- Biped dynamic walking using reinforcement learningRobotics and Autonomous Systems, 1997
- Statistical Inference, Occam's Razor, and Statistical Mechanics on the Space of Probability DistributionsNeural Computation, 1997
- Advantage Updating1993