Evaluating the Safety of Deep Reinforcement Learning Models using Semi-Formal Verification

Groundbreaking successes have been achieved by Deep Reinforcement Learning (DRL) in solving practical decision-making problems. Robotics, in particular, can involve high-cost hardware and human interactions. Hence, scrupulous evaluations of trained models are required to avoid unsafe behaviours in the operational environment. However, designing metrics to measure the safety of a neural network is an open problem, since standard evaluation parameters (e.g., total reward) are not informative enough. In this paper, we present a semi-formal verification approach for decision-making tasks, based on interval analysis, that addresses the computational demanding of previous verification frameworks and design metrics to measure the safety of the models. Our method obtains comparable results over standard benchmarks with respect to formal verifiers, while drastically reducing the computation time. Moreover, our approach allows to efficiently evaluate safety properties for decision-making models in practical applications such as mapless navigation for mobile robots and trajectory generation for manipulators.

[1]  Tom Schaul,et al.  Rainbow: Combining Improvements in Deep Reinforcement Learning , 2017, AAAI.

[2]  Pushmeet Kohli,et al.  A Unified View of Piecewise Linear Neural Network Verification , 2017, NeurIPS.

[3]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[4]  Russ Tedrake,et al.  Evaluating Robustness of Neural Networks with Mixed Integer Programming , 2017, ICLR.

[5]  Michael P. Owen,et al.  ACAS Xu: Integrated Collision Avoidance and Detect and Avoid Capability for UAS , 2019, 2019 IEEE/AIAA 38th Digital Avionics Systems Conference (DASC).

[6]  Wojciech Zaremba,et al.  OpenAI Gym , 2016, ArXiv.

[7]  Benjamin Recht,et al.  Simple random search of static linear policies is competitive for reinforcement learning , 2018, NeurIPS.

[8]  Alex Graves,et al.  Playing Atari with Deep Reinforcement Learning , 2013, ArXiv.

[9]  Richard S. Sutton,et al.  Neuronlike adaptive elements that can solve difficult learning control problems , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[10]  Wolfram Burgard,et al.  Deep reinforcement learning with successor features for navigation across similar environments , 2016, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[11]  Weiming Xiang,et al.  Output Reachable Set Estimation and Verification for Multilayer Neural Networks , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[12]  Marcin Andrychowicz,et al.  Solving Rubik's Cube with a Robot Hand , 2019, ArXiv.

[13]  Inderjit S. Dhillon,et al.  Towards Fast Computation of Certified Robustness for ReLU Networks , 2018, ICML.

[14]  Mykel J. Kochenderfer,et al.  Algorithms for Verifying Deep Neural Networks , 2019, Found. Trends Optim..

[15]  Aditi Raghunathan,et al.  Certified Defenses against Adversarial Examples , 2018, ICLR.

[16]  Junfeng Yang,et al.  Formal Security Analysis of Neural Networks using Symbolic Intervals , 2018, USENIX Security Symposium.

[17]  Antonio Criminisi,et al.  Measuring Neural Net Robustness with Constraints , 2016, NIPS.

[18]  Philip Bachman,et al.  Deep Reinforcement Learning that Matters , 2017, AAAI.

[19]  Mykel J. Kochenderfer,et al.  Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks , 2017, CAV.

[20]  Tianshu Chu,et al.  Safe Reinforcement Learning: Learning with Supervision Using a Constraint-Admissible Set , 2018, 2018 Annual American Control Conference (ACC).

[21]  Ming Liu,et al.  A deep-network solution towards model-less obstacle avoidance , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[22]  Tsang-Wei Edward Lee,et al.  Long Range Neural Navigation Policies for the Real World , 2019, 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[23]  Swarat Chaudhuri,et al.  AI2: Safety and Robustness Certification of Neural Networks with Abstract Interpretation , 2018, 2018 IEEE Symposium on Security and Privacy (SP).

[24]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[25]  Pierre-Yves Oudeyer,et al.  A Hitchhiker's Guide to Statistical Comparisons of Reinforcement Learning Algorithms , 2019, RML@ICLR.

[26]  Timon Gehr,et al.  An abstract domain for certifying neural networks , 2019, Proc. ACM Program. Lang..

[27]  Ming Liu,et al.  Virtual-to-real deep reinforcement learning: Continuous control of mobile robots for mapless navigation , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[28]  Rüdiger Ehlers,et al.  Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks , 2017, ATVA.

[29]  Jiming Liu,et al.  Reinforcement Learning in Healthcare: A Survey , 2019, ACM Comput. Surv..

[30]  Junfeng Yang,et al.  Efficient Formal Safety Analysis of Neural Networks , 2018, NeurIPS.

[31]  Javier García,et al.  A comprehensive survey on safe reinforcement learning , 2015, J. Mach. Learn. Res..

[32]  Alessio Lomuscio,et al.  An approach to reachability analysis for feed-forward ReLU neural networks , 2017, ArXiv.

[33]  Sergey Levine,et al.  Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates , 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[34]  Ramon E. Moore Interval arithmetic and automatic error analysis in digital computing , 1963 .

[35]  Weiming Xiang,et al.  Reachable Set Computation and Safety Verification for Neural Networks with ReLU Activations , 2017, ArXiv.

[36]  Ananthram Swami,et al.  The Limitations of Deep Learning in Adversarial Settings , 2015, 2016 IEEE European Symposium on Security and Privacy (EuroS&P).

[37]  Alessandro Farinelli,et al.  Genetic Deep Reinforcement Learning for Mapless Navigation , 2020, AAMAS.

[38]  Paolo Fiorini,et al.  Double Deep Q-Network for Trajectory Generation of a Commercial 7DOF Redundant Manipulator , 2019, 2019 Third IEEE International Conference on Robotic Computing (IRC).