 Safety-Gymnasium: A Unified Safe Reinforcement Learning BenchmarkNeural Information Processing Systems (NeurIPS), 2023 |
 Safe Reinforcement Learning via Probabilistic Logic ShieldsInternational Workshop on Neural-Symbolic Learning and Reasoning (NeSy), 2023 |
 Online Shielding for Reinforcement LearningInnovations in Systems and Software Engineering (ISSE), 2022 |
 Automata Learning meets ShieldingLeveraging Applications of Formal Methods (ISoLA), 2022 |
 Dynamic Shielding for Reinforcement Learning in Black-Box EnvironmentsAutomated Technology for Verification and Analysis (ATVA), 2022 |
 Safe Reinforcement Learning via Shielding under Partial ObservabilityAAAI Conference on Artificial Intelligence (AAAI), 2022 |
 Constrained Variational Policy Optimization for Safe Reinforcement
LearningInternational Conference on Machine Learning (ICML), 2022 |
 Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement
LearningConference on Robot Learning (CoRL), 2021 |
 Safe Multi-Agent Reinforcement Learning via ShieldingAdaptive Agents and Multi-Agent Systems (AAMAS), 2021 |
 Conservative Safety Critics for ExplorationInternational Conference on Learning Representations (ICLR), 2020 |
 Responsive Safety in Reinforcement Learning by PID Lagrangian MethodsInternational Conference on Machine Learning (ICML), 2020 |
 Meta-Learning in Neural Networks: A SurveyIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020 |
 Constrained Policy OptimizationInternational Conference on Machine Learning (ICML), 2017 |
