CTPR: Contrastive transition predictive representation for reinforcement learning
Authors:
- Hao SunHSHao Sun
- Changpeng WangCWChangpeng Wang
- 29 May 2025
- journal article
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 156
Abstract
No abstract availableFunding Information
- Natural Science Basic Research Program of Shaanxi Province (2019JQ-625)
- Fundamental Research Funds for the Central Universities (300102122101)
- National Natural Science Foundation of China (61976174, 12471480)
- Key Research and Development Program of Hunan Province of China (2021NY-170)
This publication has 18 references indexed in Scilit:
- Prediction of maximum tensile stress in plain-weave composite laminates with interacting holes via stacked machine learning algorithms: A comparative studyMechanical Systems and Signal Processing, 2023
- Machine learning-based seismic response and performance assessment of reinforced concrete buildingsArchives of Civil and Mechanical Engineering, 2023
- Machine learning-based seismic fragility and seismic vulnerability assessment of reinforced concrete structuresSoil Dynamics and Earthquake Engineering, 2023
- Hybrid attention-oriented experience replay for deep reinforcement learning and its application to a multi-robot cooperative hunting problemNeurocomputing, 2022
- Self-supervised representation learning for trip recommendationKnowledge-Based Systems, 2022
- Hybrid autonomous controller for bipedal robot balance with deep reinforcement learning and pattern generatorsRobotics and Autonomous Systems, 2021
- Grandmaster level in StarCraft II using multi-agent reinforcement learningNature, 2019
- Building machines that learn and think like peopleBehavioral and Brain Sciences, 2016
- Human-level control through deep reinforcement learningNature, 2015
- Planning and acting in partially observable stochastic domainsArtificial Intelligence, 1998