Dual-critic constrained deceptive Q-learning for deployment-time policy protection
Open Access
- 17 August 2026
- journal article
- research article
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 38 (7) , 657
Abstract
No abstract availableKeywords
Funding Information
- Youth Science Fund Project (No. 62003363)
- Natural Science Basic Research Program of Shaanxi Province (No. 2022KJXX-99)
- Fundamental and Frontier Innovation Program (2025-QYCX-ZD-03-026)
This publication has 24 references indexed in Scilit:
- Deep reinforcement learning in recommender systems: A survey and new perspectivesKnowledge-Based Systems, 2023
- Deep reinforcement learning for inventory control: A roadmapEuropean Journal of Operational Research, 2022
- Challenges of real-world reinforcement learning: definitions, benchmarks and analysisMachine Learning, 2021
- Deep Reinforcement Learning for Autonomous Driving: A SurveyIEEE Transactions on Intelligent Transportation Systems, 2021
- Knockoff Nets: Stealing Functionality of Black-Box Models2019
- Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks2017
- Membership Inference Attacks Against Machine Learning Models2017
- Human-level control through deep reinforcement learningNature, 2015
- Calibrating Noise to Sensitivity in Private Data Analysis2006
- A framework for behavioural cloning2000