{"total":39,"rows":[{"id":"2106.13906","title":"Compositional Reinforcement Learning from Logical Specifications","created":"2021-06-25","cited_by_count":67,"area":null},{"id":"2302.11649","title":"Grounding Complex Natural Language Commands for Temporal Tasks in Unseen Environments","created":"2023-02-22","cited_by_count":53,"area":null},{"id":"2303.03226","title":"Safe Reinforcement Learning via Probabilistic Logic Shields","created":"2023-03-06","cited_by_count":42,"area":null},{"id":"2109.09904","title":"Symbols as a Lingua Franca for Bridging Human-AI Chasm for Explainable and Advisable AI Systems","created":"2021-09-21","cited_by_count":36,"area":null},{"id":"2205.06750","title":"Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarking","created":"2022-05-13","cited_by_count":34,"area":null},{"id":"2102.12571","title":"The Logical Options Framework","created":"2021-02-24","cited_by_count":25,"area":null},{"id":"2202.02886","title":"Leveraging Approximate Symbolic Models for Reinforcement Learning via Skill Diversity","created":"2022-02-06","cited_by_count":22,"area":null},{"id":"2111.12679","title":"On the (In)Tractability of Reinforcement Learning for LTL Objectives","created":"2021-11-24","cited_by_count":18,"area":null},{"id":"2205.06311","title":"Provably Safe Deep Reinforcement Learning for Robotic Manipulation in Human Environments","created":"2022-05-12","cited_by_count":18,"area":null},{"id":"2305.01381","title":"Sample Efficient Model-free Reinforcement Learning from LTL Specifications with Optimality Guarantees","created":"2023-05-02","cited_by_count":18,"area":null},{"id":"2305.17115","title":"Policy Synthesis and Reinforcement Learning for Discounted LTL","created":"2023-05-26","cited_by_count":14,"area":null},{"id":"2303.05518","title":"Computably Continuous Reinforcement-Learning Objectives are PAC-learnable","created":"2023-03-09","cited_by_count":13,"area":null},{"id":"2209.10341","title":"LCRL: Certified Policy Synthesis via Logically-Constrained Reinforcement Learning","created":"2022-09-21","cited_by_count":11,"area":null},{"id":"2205.01053","title":"Markov Abstractions for PAC Reinforcement Learning in Non-Markov Decision Processes","created":"2022-04-29","cited_by_count":10,"area":null},{"id":"2206.03348","title":"Specification-Guided Learning of Nash Equilibria with High Social Welfare","created":"2022-06-06","cited_by_count":8,"area":null},{"id":"2303.09172","title":"Learning Logic Specifications for Soft Policy Guidance in POMCP","created":"2023-03-16","cited_by_count":7,"area":null},{"id":"2303.04592","title":"Controlled Diversity with Preference : Towards Learning a Diverse Set of Desired Skills","created":"2023-03-07","cited_by_count":6,"area":null},{"id":"2109.07195","title":"Target Languages (vs. Inductive Biases) for Learning to Act and Plan","created":"2021-09-15","cited_by_count":5,"area":null},{"id":"2111.09475","title":"Lifelong Reinforcement Learning with Temporal Logic Formulas and Reward Machines","created":"2021-11-18","cited_by_count":5,"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":"2411.01184","title":"Guiding Multi-agent Multi-task Reinforcement Learning by a Hierarchical Framework with Logical Reward Shaping","created":"2024-11-02","cited_by_count":4,"area":null},{"id":"2305.08319","title":"Model Checking Strategies from Synthesis Over Finite Traces","created":"2023-05-15","cited_by_count":3,"area":null},{"id":"2105.14894","title":"LTL-Constrained Steady-State Policy Synthesis","created":"2021-05-31","cited_by_count":2,"area":null},{"id":"2106.11735","title":"Lifted Model Checking for Relational MDPs","created":"2021-06-22","cited_by_count":2,"area":null},{"id":"2204.09960","title":"Planning for Temporally Extended Goals in Pure-Past Linear Temporal Logic: A Polynomial Reduction to Standard Planning","created":"2022-04-21","cited_by_count":2,"area":null},{"id":"2402.07547","title":"Ensuring trustworthy and ethical behaviour in intelligent logical agents","created":"2024-02-12","cited_by_count":2,"area":null},{"id":"2104.14089","title":"Collaborative Human-Agent Planning for Resilience","created":"2021-04-29","cited_by_count":1,"area":null},{"id":"2111.03647","title":"Regular Decision Processes for Grid Worlds","created":"2021-11-05","cited_by_count":1,"area":null},{"id":"2203.15398","title":"Learning to act: a Reinforcement Learning approach to recommend the best next activities","created":"2022-03-29","cited_by_count":1,"area":null},{"id":"2211.14028","title":"Automata Cascades: Expressivity and Sample Complexity","created":"2022-11-25","cited_by_count":1,"area":null},{"id":"2312.11314","title":"Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis","created":"2023-12-18","cited_by_count":1,"area":null},{"id":"2205.09201","title":"Mimicking Behaviors in Separated Domains","created":"2022-05-18","cited_by_count":0,"area":null},{"id":"2207.04479","title":"Scaling up ML-based Black-box Planning with Partial STRIPS Models","created":"2022-07-10","cited_by_count":0,"area":null},{"id":"2211.03461","title":"Learning Probabilistic Temporal Safety Properties from Examples in Relational Domains","created":"2022-11-07","cited_by_count":0,"area":null},{"id":"2211.12151","title":"Reinforcement Causal Structure Learning on Order Graph","created":"2022-11-22","cited_by_count":0,"area":null},{"id":"2409.09485","title":"Enumerating Minimal Unsatisfiable Cores of LTLf formulas","created":"2024-09-14","cited_by_count":0,"area":null},{"id":"2508.04116","title":"A Compositional Framework for On-the-Fly LTLf Synthesis","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2602.03486","title":"DeepDFA: Injecting Temporal Logic in Deep Learning for Sequential Subsymbolic Applications","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2606.30966","title":"HyPOLE: Hyperproperty-Guided Multi-Agent Reinforcement Learning under Partial Observation","created":"2026-06-29","cited_by_count":0,"area":null}],"next_cursor":null}