Hierarchical automatic curriculum learning: Converting a sparse reward navigation task into dense reward
Authors:
- Nan JiangNJNan Jiang
- Sheng JinSJSheng Jin
- Changshui ZhangCZChangshui Zhang
- 1 September 2019
- journal article
- research article
- Published by Elsevier in Neurocomputing
- Vol. 360, 265-278
Abstract
No abstract availableKeywords
Funding Information
- NSFC (61876095, 61751308)
This publication has 6 references indexed in Scilit:
- Self-Paced Prioritized Curriculum Learning With Coverage Penalty in Deep Reinforcement LearningIEEE Transactions on Neural Networks and Learning Systems, 2018
- Path planning of multi-agent systems in unknown environment with neural kernel smoothing and reinforcement learningNeurocomputing, 2017
- Mastering the game of Go with deep neural networks and tree searchNature, 2016
- A hierarchical path planning approach based on A ⁎ and least-squares policy iteration for mobile robotsNeurocomputing, 2015
- Human-level control through deep reinforcement learningNature, 2015
- Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learningArtificial Intelligence, 1999