{"total":27,"rows":[{"id":"2303.03226","title":"Safe Reinforcement Learning via Probabilistic Logic Shields","created":"2023-03-06","cited_by_count":42,"area":null},{"id":"2310.03225","title":"Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms","created":"2023-10-05","cited_by_count":28,"area":null},{"id":"2408.05284","title":"Can a Bayesian Oracle Prevent Harm from an Agent?","created":"2024-08-09","cited_by_count":13,"area":null},{"id":"2210.01801","title":"Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation","created":"2022-10-02","cited_by_count":11,"area":null},{"id":"2303.05848","title":"Decision-Making Under Uncertainty: Beyond Probabilities","created":"2023-03-10","cited_by_count":9,"area":null},{"id":"2308.14424","title":"Shielded Reinforcement Learning for Hybrid Systems","created":"2023-08-28","cited_by_count":8,"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":"2309.10216","title":"Safe POMDP Online Planning via Shielding","created":"2023-09-19","cited_by_count":8,"area":null},{"id":"2307.14316","title":"Reinforcement Learning by Guided Safe Exploration","created":"2023-07-26","cited_by_count":7,"area":null},{"id":"2408.08770","title":"Pessimistic Iterative Planning with RNNs for Robust POMDPs","created":"2024-08-16","cited_by_count":7,"area":null},{"id":"2304.12090","title":"Reinforcement Learning with Knowledge Representation and Reasoning: A Brief Survey","created":"2023-04-24","cited_by_count":5,"area":null},{"id":"2307.02164","title":"Safety Shielding under Delayed Observation","created":"2023-07-05","cited_by_count":3,"area":null},{"id":"2506.17275","title":"Conformal Safety Shielding for Imperfect-Perception Agents","created":"2025-06-12","cited_by_count":3,"area":null},{"id":"2304.11104","title":"Approximate Shielding of Atari Agents for Safe Exploration","created":"2023-04-21","cited_by_count":2,"area":null},{"id":"2605.10888","title":"Shields to Guarantee Probabilistic Safety in MDPs","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2411.04867","title":"Think Smart, Act SMARL! Analyzing Probabilistic Logic Shields for Multi-Agent Reinforcement Learning","created":"2024-11-07","cited_by_count":1,"area":null},{"id":"2306.14816","title":"Experiments with Detecting and Mitigating AI Deception","created":"2023-06-26","cited_by_count":0,"area":null},{"id":"2310.04288","title":"Searching for Optimal Runtime Assurance via Reachability and Reinforcement Learning","created":"2023-10-06","cited_by_count":0,"area":null},{"id":"2505.22104","title":"Efficient Dynamic Shielding for Parametric Safety Specifications","created":"2025-05-28","cited_by_count":0,"area":null},{"id":"2603.02396","title":"COOL-MC: Verifying and Explaining RL Policies for Platelet Inventory Management","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2604.20728","title":"Interval POMDP Shielding for Imperfect-Perception Agents","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.14246","title":"Action-Conditioned Risk Gating for Safety-Critical Control under Partial Observability","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.24926","title":"Energy Shields for Fairness","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2606.13621","title":"Shielded Analysis: Certification and Characterization of Defensibility in Systems under Adversarial Interaction","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2608.03662","title":"Shielding for Higher-Order Safety","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.16056","title":"Managing Action Preconditions in Neuro-Symbolic RL: Three Placement Strategies for Embodied Agents","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2610.04975","title":"Runtime Authorization of Self-Generated Subgoals in Long-Horizon Tool-Using AI Agents","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}