Learning and Repair of Deep Reinforcement Learning Policies from Fuzz-Testing Data-Reference-Cited by-同舟云学术

Learning and Repair of Deep Reinforcement Learning Policies from Fuzz-Testing Data

Published:2024-02-06 Issue: Volume:123 Page:1-13
ISSN:
Container-title:Proceedings of the IEEE/ACM 46th International Conference on Software Engineering
language:
Short-container-title:

Author:

Tappler Martin¹²^ORCID,Pferscher Andrea¹^ORCID,Aichernig Bernhard K.¹^ORCID,Könighofer Bettina³^ORCID

Affiliation:

1. Institute of Software Technology, Graz University of Technology, Graz, Austria

2. TU Graz - SAL, DES Lab, Silicon Austria Labs, Graz, Austria

3. Institute of Applied Information Processing and Communications, Graz University of Technology, Graz, Austria

Funder

EU Horizon 2020

State Government of Styria, Austria ? Department Zukunftsfonds Steiermark

Silicon Austria Labs (SAL) - University SAL Lab initiative

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3597503.3623311

Reference49 articles.

1. Learning a Behavior Model of Hybrid Systems Through Combining Model-Based Testing and Machine Learning

2. Yusuf Aytar, Tobias Pfaff, David Budden, Tom Le Paine, Ziyu Wang, and Nando de Freitas. 2018. Playing Hard Exploration Games by Watching YouTube. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3--8, 2018, Montréal, Canada. 2935--2945. https://proceedings.neurips.cc/paper/2018/hash/35309226eb45ec366ca86a4329a2b7c3-Abstract.html

3. Matteo Biagiola and Paolo Tonella. 2023. Testing of Deep Reinforcement Learning Agents with Surrogate Models. arXiv:2305.12751 [cs.SE]

4. Active deep Q-learning with demonstration

5. Maxime Chevalier-Boisvert, Bolun Dai, Mark Towers, Rodrigo de Lazcano, Lucas Willems, Salem Lahlou, Suman Pal, Pablo Samuel Castro, and Jordan Terry. 2023. Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks. CoRR abs/2306.13831 (2023).

Cited by 1 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Learning Environment Models with Continuous Stochastic Dynamics - with an Application to Deep RL Testing;2024 IEEE Conference on Software Testing, Verification and Validation (ICST);2024-05-27