{"total":9,"rows":[{"id":"2107.12045","title":"How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review","created":"2021-07-26","cited_by_count":39,"area":null},{"id":"2211.02147","title":"A Survey on Reinforcement Learning in Aviation Applications","created":"2022-11-03","cited_by_count":19,"area":null},{"id":"2202.05195","title":"Uncovering Instabilities in Variational-Quantum Deep Q-Networks","created":"2022-02-10","cited_by_count":14,"area":null},{"id":"2305.00224","title":"An Empirical Comparison of Optimizers for Quantum Machine Learning with SPSA-based Gradients","created":"2023-04-27","cited_by_count":14,"area":null},{"id":"2309.06239","title":"Risk-Aware Reinforcement Learning through Optimal Transport Theory","created":"2023-09-12","cited_by_count":8,"area":null},{"id":"2404.15751","title":"Guided-SPSA: Simultaneous Perturbation Stochastic Approximation assisted by the Parameter Shift Rule","created":"2024-04-24","cited_by_count":4,"area":null},{"id":"2205.04590","title":"A Verification Framework for Certifying Learning-Based Safety-Critical Aviation Systems","created":"2022-05-09","cited_by_count":3,"area":null},{"id":"2305.00576","title":"Joint Learning of Policy with Unknown Temporal Constraints for Safe Reinforcement Learning","created":"2023-04-30","cited_by_count":1,"area":null},{"id":"2305.06796","title":"Towards Theoretical Understanding of Data-Driven Policy Refinement","created":"2023-05-11","cited_by_count":0,"area":null}],"next_cursor":null}