A Prioritized objective actor-critic method for deep reinforcement learning
- 19 February 2021
- journal article
- research article
- Published by Springer Nature in Neural Computing & Applications
- Vol. 33 (16), 10335-10349
- https://doi.org/10.1007/s00521-021-05795-0
Abstract
No abstract availableKeywords
This publication has 19 references indexed in Scilit:
- Novelty-organizing team of classifiers in noisy and dynamic environmentsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Human-level control through deep reinforcement learningNature, 2015
- Learning to select and generalize striking movements in robot table tennisThe International Journal of Robotics Research, 2013
- Empirical evaluation methods for multiobjective reinforcement learning algorithmsMachine Learning, 2010
- Reinforcement learning for robot soccerAutonomous Robots, 2009
- Learning Multiple Goal-Directed Actions Through Self-Organization of a Dynamic Neural Network Model: A Humanoid Robot ExperimentAdaptive Behavior, 2008
- On the Limitations of Scalarisation for Multi-objective Reinforcement Learning of Pareto FrontsLecture Notes in Computer Science, 2008
- Autonomous Inverted Helicopter Flight via Reinforcement LearningPublished by Springer Nature ,2006
- Apprenticeship learning via inverse reinforcement learningPublished by Association for Computing Machinery (ACM) ,2004
- Reinforcement Learning: An IntroductionIEEE Transactions on Neural Networks, 1998