2000 character limit reached
A Review of Validation and Verification of Neural Network-based Policies for Sequential Decision Making
Published 15 Dec 2023 in cs.SE | (2312.09680v1)
Abstract: In sequential decision making, neural networks (NNs) are nowadays commonly used to represent and learn the agent's policy. This area of application has implied new software quality assessment challenges that traditional validation and verification practises are not able to handle. Subsequently, novel approaches have emerged to adapt those techniques to NN-based policies for sequential decision making. This survey paper aims at summarising these novel contributions and proposing future research directions. We conducted a literature review of recent research papers (from 2018 to beginning of 2023), whose topics cover aspects of the test or verification of NN-based policies. The selection has been enriched by a snowballing process from the previously selected papers, in order to relax the scope of the study and provide the reader with insight into similar verification challenges and their recent solutions. 18 papers have been finally selected. Our results show evidence of increasing interest for this subject. They highlight the diversity of both the exact problems considered and the techniques used to tackle them.
- The Cambridge Handbook of Artificial Intelligence. Cambridge University Press, 2014. 10.1017/CBO9781139046855.
- State-of-the-art in artificial neural network applications: A survey. Heliyon, 2018.
- Verification of rnn-based neural agent-environment systems. Proceedings of the AAAI Conference on Artificial Intelligence, 2019.
- Jani: Quantitative model and tool interaction. In Axel Legay and Tiziana Margaria, editors, Tools and Algorithms for the Construction and Analysis of Systems, 2017.
- Metamorphic Testing: A New Approach for Generating Next Test Cases. Technical report, Department of Computer Science, Hong Kong University of Science and Technology, 1998.
- Chapter 24 - model checking. In Handbook of Automated Reasoning. North-Holland, 2001.
- Formal verification of neural networks for safety-critical tasks in deep reinforcement learning. In Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, 2021.
- A survey of algorithms for black-box safety validation of cyber-physical systems. J. Artif. Int. Res., 2022.
- Deepstellar: Model-based quantitative analysis of stateful deep learning systems. In Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2019.
- Metamorphic relations via relaxations: An approach to obtain oracles for action-policy testing. In Proceedings of the 31st ACM SIGSOFT International Symposium on Software Testing and Analysis, 2022.
- Verifying controllers against adversarial examples with bayesian optimization. CoRR, 2018.
- Construction of abstract state graphs with pvs. In Computer Aided Verification, 1997.
- Dsmc evaluation stages: Fostering robust and safe behavior in deep reinforcement learning. In Alessandro Abate and Andrea Marin, editors, Quantitative Evaluation of Systems, 2021.
- Mogym: Using formal models for training and verifying decision-making agents. In Sharon Shoham and Yakir Vizel, editors, Computer Aided Verification, 2022a.
- Analyzing neural network behavior through deep statistical model checking. International Journal on Software Tools for Technology Transfer, 2022b.
- Efficient online testing for dnn-enabled systems using surrogate-assisted and many-objective optimization. In 2022 IEEE/ACM 44th International Conference on Software Engineering (ICSE), 2022a.
- Many-objective reinforcement learning for online testing of dnn-enabled systems, 2022b.
- Approximate probabilistic model checking. In Bernhard Steffen and Giorgio Levi, editors, Verification, Model Checking, and Abstract Interpretation, 2004.
- John H. Holland. Genetic algorithms. Scientific American, 1992.
- Training deep reactive policies for probabilistic planning problems. Proceedings of the International Conference on Automated Planning and Scheduling, 2018.
- Learning generalized relational heuristic networks for model-agnostic planning. CoRR, 2020.
- Learning configurations of operating environment of autonomous vehicles to maximize their collisions. IEEE Transactions on Software Engineering, 2023.
- Recurrent neural networks for prediction: Learning algorithms, architectures and stability. 2001.
- William M. McKeeman. Differential testing for software. Digit. Tech. J., 1998.
- Phil McMinn. Search-based software testing: Past, present and future. In 2011 IEEE Fourth International Conference on Software Testing, Verification and Validation Workshops, 2011.
- Ramon Edgar Moore. Interval Arithmetic and Automatic Error Analysis in Digital Computing. PhD thesis, 1963.
- Mdpfuzz: Testing models solving markov decision processes. In Proceedings of the 31st ACM SIGSOFT International Symposium on Software Testing and Analysis, 2022.
- Deepxplore: Automated whitebox testing of deep learning systems. Commun. ACM, 2019.
- Mastering the game of go with deep neural networks and tree search. Nature, 2016.
- A general reinforcement learning algorithm that masters chess, shogi, and go through self-play. Science, 2018.
- Debugging a policy: Automatic action-policy testing in ai planning. Proceedings of the International Conference on Automated Planning and Scheduling, 2022.
- How to certify machine learning based safety-critical systems? a systematic literature review. Automated Software Engg., 2022.
- Search-based testing of reinforcement learning, 2022.
- Deeptest: Automated testing of deep-neural-network-driven autonomous cars. In Proceedings of the 40th International Conference on Software Engineering, 2018.
- Asnets: Deep learning for generalised planning. CoRR, 2019.
- Neural Policy Verification via Predicate Abstraction: CEGAR. page 9, 2022.
- Neural network action policy verification via predicate abstraction. Proceedings of the International Conference on Automated Planning and Scheduling, 2022.
- Reachable set estimation and safety verification for piecewise linear systems with neural network controllers. In 2018 Annual American Control Conference (ACC), 2018.
- Deephunter: A coverage-guided fuzz testing framework for deep neural networks. In Proceedings of the 28th ACM SIGSOFT International Symposium on Software Testing and Analysis, 2019.
- Testing and verification of neural-network-based safety-critical control software: A systematic literature review. Information and Software Technology, 2020.
- Deeproad: Gan-based metamorphic testing and input validation framework for autonomous driving systems. In Proceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineering, 2018.
- A search-based testing approach for deep reinforcement learning agents, 2023.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.