Dependability Analysis of Deep Reinforcement Learning based Robotics and Autonomous Systems through Probabilistic Model Checking
Not on the map. Why?
Abstract (arXiv)
While Deep Reinforcement Learning (DRL) provides transformational capabilities to the control of Robotics and Autonomous Systems (RAS), the black-box nature of DRL and uncertain deployment environments of RAS pose new challenges on its dependability. Although existing works impose constraints on the DRL policy to ensure successful completion of the mission, it is far from adequate to assess the DRL-driven RAS in a holistic way considering all dependability properties. In this paper, we formally define a set of dependability properties in temporal logic and construct a Discrete-Time Markov Chain (DTMC) to model the dynamics of risk/failures of a DRL-driven RAS interacting with the stochastic environment. We then conduct Probabilistic Model Checking (PMC) on the designed DTMC to verify those properties. Our experimental results show that the proposed method is effective as a holistic assessment framework while uncovering conflicts between the properties that may need trade-offs in training. Moreover, we find that the standard DRL training cannot improve dependability properties, thus requiring bespoke optimisation objectives. Finally, our method offers sensitivity analysis of dependability properties to disturbance levels from environments, providing insights for the assurance of real RAS.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 25 of its 52 references that are in the map. First posted on arXiv 14 Sep 2021.
Builds on
25 of 52 references.
References · 25
- 2015Continuous control with deep reinforcement learningcited by 3,407
- 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
- 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
- 2017Safe Reinforcement Learning via Shieldingcited by 449
- 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 413
- 2017Safe Model-based Reinforcement Learning with Stability Guaranteescited by 366
- 2019End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Taskscited by 289
- 2019Google Research Football: A Novel Reinforcement Learning Environmentcited by 260
- 2020Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observationscited by 238
- 2017Deep Reinforcement Learning framework for Autonomous Drivingcited by 225
- 2018Verifiable Reinforcement Learning via Policy Extractioncited by 177
- 2019Action Robust Reinforcement Learning and Applications in Continuous Controlcited by 174
13 more
- 2017Emergent Complexity via Multi-Agent Competitioncited by 120
- 2018Reachability Analysis of Deep Neural Networks with Provable Guaranteescited by 93
- 2019Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewardscited by 64
- 2016Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Modelcited by 54
- 2019An Inductive Synthesis Framework for Verifiable Reinforcement Learningcited by 39
- 2017A storm is Coming: A Modern Probabilistic Model Checkercited by 34
- 2020Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approachcited by 13
- 2018Probabilistic Model Checking of Robots Deployed in Extreme Environmentscited by 12
- 2018Adversarial Reinforcement Learning Framework for Benchmarking Collision Avoidance Mechanisms in Autonomous Vehiclescited by 8
- 2021Scalable Synthesis of Verified Controllers in Deep Reinforcement Learningcited by 5
- 2018Efficient Parametric Model Checking Using Domain Knowledgecited by 2
- 2019Towards Integrating Formal Verification of Autonomous Robots with Battery Prognostics and Health Managementcited by 2
- 2020Towards Identifying and closing Gaps in Assurance of autonomous Road vehicleS -- a collection of Technical Notes Part 2cited by 1
Built on by
Citing papers per year: 2022: 1; 2023: 0; 2024: 0; 2025: 0; 2026: 2.
3 papers.