Counterexample-Guided Repair of Reinforcement Learning Systems Using Safety Critics
Not on the map. Why?
Abstract (arXiv)
Naively trained Deep Reinforcement Learning agents may fail to satisfy vital safety constraints. To avoid costly retraining, we may desire to repair a previously trained reinforcement learning agent to obviate unsafe behaviour. We devise a counterexample-guided repair algorithm for repairing reinforcement learning systems leveraging safety critics. The algorithm jointly repairs a reinforcement learning agent and a safety critic using gradient-based constrained optimisation.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 15 of its 38 references that are in the map. First posted on arXiv 24 May 2024.
Builds on
15 of 38 references.
References · 15
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
- 2017Safe Reinforcement Learning via Shieldingcited by 427
- 2020NNV: The Neural Network Verification Tool for Deep Neural Networks and Learning-Enabled Cyber-Physical Systemscited by 128
- 2020Learning to be Safe: Deep RL with a Safety Criticcited by 109
- 2020Conservative Safety Critics for Explorationcited by 107
- 2022General Cutting Planes for Bound-Propagation-Based Neural Network Verificationcited by 102
- 2018Verisig: verifying safety properties of hybrid systems with neural network controllerscited by 83
- 2016Scalable Learning of Non-Decomposable Objectivescited by 40
- 2021Provable Repair of Deep Neural Networkscited by 39
- 2020Towards Repairing Neural Networks Correctlycited by 13
- 2023Architecture-Preserving Provable Repair of Deep Neural Networkscited by 9
Built on by
Citing papers per year: 2026: 1.
1 paper.