{"total":75,"rows":[{"id":"2101.11196","title":"Safe Multi-Agent Reinforcement Learning via Shielding","created":"2021-01-27","cited_by_count":61,"area":null},{"id":"2102.12855","title":"Modular Deep Reinforcement Learning for Continuous Motion Planning with Temporal Logic","created":"2021-02-24","cited_by_count":39,"area":null},{"id":"2102.00582","title":"Multi-Agent Reinforcement Learning with Temporal Logic Specifications","created":"2021-02-01","cited_by_count":27,"area":null},{"id":"2410.04631","title":"DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RL","created":"2024-10-06","cited_by_count":21,"area":"deeprl"},{"id":"2206.09546","title":"Policy Optimization with Linear Temporal Logic Constraints","created":"2022-06-20","cited_by_count":19,"area":null},{"id":"2303.02135","title":"Eventual Discounting Temporal Logic Counterfactual Experience Replay","created":"2023-03-03","cited_by_count":19,"area":null},{"id":"2411.00205","title":"Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning","created":"2024-10-31","cited_by_count":19,"area":"deeprl"},{"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":"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":"2312.01456","title":"Compositional Policy Learning in Stochastic Control Systems with Formal Guarantees","created":"2023-12-03","cited_by_count":14,"area":null},{"id":"2410.12175","title":"Reinforcement Learning with LTL and $\\omega$-Regular Objectives via Optimality-Preserving Translation to Average Rewards","created":"2024-10-16","cited_by_count":14,"area":"deeprl"},{"id":"2303.05518","title":"Computably Continuous Reinforcement-Learning Objectives are PAC-learnable","created":"2023-03-09","cited_by_count":13,"area":null},{"id":"2310.12248","title":"A PAC Learning Algorithm for LTL and Omega-regular Objectives in MDPs","created":"2023-10-18","cited_by_count":13,"area":null},{"id":"2204.11833","title":"Joint Learning of Reward Machines and Policies in Environments with Partially Known Semantics","created":"2022-04-20","cited_by_count":12,"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":"2304.06281","title":"Model-based Dynamic Shielding for Safe and Efficient Multi-Agent Reinforcement Learning","created":"2023-04-13","cited_by_count":11,"area":null},{"id":"2310.09454","title":"LgTS: Dynamic Task Sampling using LLM-generated sub-goals for Reinforcement Learning Agents","created":"2023-10-14","cited_by_count":11,"area":"lr"},{"id":"2404.11578","title":"LTL-Constrained Policy Optimization with Cycle Experience Replay","created":"2024-04-17","cited_by_count":11,"area":"deeprl"},{"id":"2402.17217","title":"Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement Learning","created":"2024-02-27","cited_by_count":10,"area":"offlinerl"},{"id":"2205.04424","title":"Accelerated Reinforcement Learning for Temporal Logic Control Objectives","created":"2022-05-09","cited_by_count":9,"area":null},{"id":"2408.09495","title":"Directed Exploration in Reinforcement Learning from Linear Temporal Logic","created":"2024-08-18","cited_by_count":7,"area":"deeprl"},{"id":"2106.09161","title":"Mungojerrie: Reinforcement Learning of Linear-Time Objectives","created":"2021-06-16","cited_by_count":6,"area":null},{"id":"2412.10917","title":"Adaptive Reward Design for Reinforcement Learning","created":"2024-12-14","cited_by_count":6,"area":"deeprl"},{"id":"2103.14600","title":"Model-Free Learning of Safe yet Effective Controllers","created":"2021-03-26","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":"2410.12136","title":"Sample-Efficient Reinforcement Learning with Temporal Logic Objectives: Leveraging the Task Specification to Guide Exploration","created":"2024-10-16","cited_by_count":5,"area":"deeprl"},{"id":"2102.04307","title":"Learning Optimal Strategies for Temporal Tasks in Stochastic Games","created":"2021-02-08","cited_by_count":3,"area":null},{"id":"2206.08881","title":"Logic-based Reward Shaping for Multi-Agent Reinforcement Learning","created":"2022-06-17","cited_by_count":3,"area":null},{"id":"2311.17059","title":"Mission-driven Exploration for Accelerated Deep Reinforcement Learning with Temporal Logic Task Specifications","created":"2023-11-28","cited_by_count":3,"area":null},{"id":"2402.03678","title":"Logical Specifications-guided Dynamic Task Sampling for Reinforcement Learning Agents","created":"2024-02-06","cited_by_count":3,"area":"deeprl"},{"id":"2404.05074","title":"On the Uniqueness of Solution for the Bellman Equation of LTL Objectives","created":"2024-04-07","cited_by_count":3,"area":null},{"id":"2409.02747","title":"Tractable Offline Learning of Regular Decision Processes","created":"2024-09-04","cited_by_count":3,"area":"offlinerl"},{"id":"2101.10284","title":"Reinforcement Learning Based Temporal Logic Control with Soft Constraints Using Limit-deterministic Generalized Buchi Automata","created":"2021-01-25","cited_by_count":2,"area":null},{"id":"2209.11789","title":"SAFER: Safe Collision Avoidance using Focused and Efficient Trajectory Search with Reinforcement Learning","created":"2022-09-23","cited_by_count":2,"area":null},{"id":"2303.01346","title":"Co-learning Planning and Control Policies Constrained by Differentiable Logic Specifications","created":"2023-03-02","cited_by_count":2,"area":null},{"id":"2305.14736","title":"Optimal Control of Logically Constrained Partially Observable and Multi-Agent Markov Decision Processes","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2308.07469","title":"Omega-Regular Reward Machines","created":"2023-08-14","cited_by_count":2,"area":null},{"id":"2505.12107","title":"Learning Probabilistic Temporal Logic Specifications for Stochastic Systems","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2601.22891","title":"PlatoLTL: Scaling LTL-Guided Multi-Task RL","created":"2026-01-30","cited_by_count":2,"area":"deeprl"},{"id":"2602.06746","title":"Semantically Labelled Automata for Multi-Task Reinforcement Learning with LTL Instructions","created":"2026-02-06","cited_by_count":2,"area":"deeprl"},{"id":"2109.02791","title":"Safety-Critical Learning of Robot Control with Temporal Logic Specifications","created":"2021-09-07","cited_by_count":1,"area":null},{"id":"2112.10714","title":"Learning Spatio-Temporal Specifications for Dynamical Systems","created":"2021-12-20","cited_by_count":1,"area":null},{"id":"2205.10464","title":"Synthesis from Satisficing and Temporal Goals","created":"2022-05-20","cited_by_count":1,"area":null},{"id":"2303.09528","title":"Reinforcement Learning for Omega-Regular Specifications on Continuous-Time MDP","created":"2023-03-16","cited_by_count":1,"area":null},{"id":"2305.00561","title":"Model-free Motion Planning of Autonomous Agents for Complex Tasks in Partially Observable Environments","created":"2023-04-30","cited_by_count":1,"area":null},{"id":"2411.01425","title":"Learning Hidden Subgoals under Temporal Ordering Constraints in Reinforcement Learning","created":"2024-11-03","cited_by_count":1,"area":"deeprl"},{"id":"2506.01167","title":"Accelerated Learning with Linear Temporal Logic using Differentiable Simulation","created":"2025-06-01","cited_by_count":1,"area":"deeprl"},{"id":"2602.14344","title":"Zero-Shot Instruction Following in RL via Structured LTL Representations","created":"2026-02-15","cited_by_count":1,"area":"deeprl"},{"id":"2604.24729","title":"SpecRLBench: A Benchmark for Generalization in Specification-Guided Reinforcement Learning","created":"2026-04-27","cited_by_count":1,"area":"deeprl"},{"id":"2106.01977","title":"Safe RAN control: A Symbolic Reinforcement Learning Approach","created":"2021-06-03","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":"2310.04288","title":"Searching for Optimal Runtime Assurance via Reachability and Reinforcement Learning","created":"2023-10-06","cited_by_count":0,"area":null},{"id":"2310.11678","title":"Using Experience Classification for Training Non-Markovian Tasks","created":"2023-10-18","cited_by_count":0,"area":null},{"id":"2311.10863","title":"Verified Compositional Neuro-Symbolic Control for Stochastic Systems with Temporal Logic Tasks","created":"2023-11-17","cited_by_count":0,"area":null},{"id":"2312.08602","title":"Omega-Regular Decision Processes","created":"2023-12-14","cited_by_count":0,"area":null},{"id":"2401.14226","title":"Sample Efficient Reinforcement Learning by Automatically Learning to Compose Subtasks","created":"2024-01-25","cited_by_count":0,"area":"deeprl"},{"id":"2403.15826","title":"Scaling Learning based Policy Optimization for Temporal Logic Tasks by Controller Network Dropout","created":"2024-03-23","cited_by_count":0,"area":null},{"id":"2505.15693","title":"Average Reward Reinforcement Learning for Omega-Regular and Mean-Payoff Objectives","created":"2025-05-21","cited_by_count":0,"area":"deeprl"},{"id":"2508.00106","title":"Hyperproperty-Constrained Secure Reinforcement Learning","created":"2025-07-31","cited_by_count":0,"area":"deeprl"},{"id":"2508.14093","title":"Physics-Informed Reward Machines","created":"2025-08-14","cited_by_count":0,"area":"deeprl"},{"id":"2510.07715","title":"Control Synthesis of Cyber-Physical Systems for Real-Time Specifications through Causation-Guided Reinforcement Learning","created":"2025-10-09","cited_by_count":0,"area":"deeprl"},{"id":"2511.19849","title":"Near-Optimal Reinforcement Learning for Constrained Recurrence Objectives","created":"2025-11-25","cited_by_count":0,"area":"deeprl"},{"id":"2512.02633","title":"Zero-Shot Instruction Following in RL via Structured LTL Representations","created":"2025-12-02","cited_by_count":0,"area":"deeprl"},{"id":"2512.17637","title":"About Time: Model-free Reinforcement Learning with Timed Reward Machines","created":"2025-12-19","cited_by_count":0,"area":"deeprl"},{"id":"2602.06227","title":"Do It for HER: First-Order Temporal Logic Reward Specification in Reinforcement Learning (Extended Version)","created":"2026-02-05","cited_by_count":0,"area":"deeprl"},{"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":"2603.07546","title":"COOL-MC: Verifying and Explaining RL Policies for Multi-bridge Network Maintenance","created":"2026-03-08","cited_by_count":0,"area":"deeprl"},{"id":"2605.15975","title":"Learning Bilevel Policies over Symbolic World Models for Long-Horizon Planning","created":"2026-05-15","cited_by_count":0,"area":"wm"},{"id":"2605.31524","title":"Value Functions as Supermartingale Certificates","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2608.05047","title":"Exact Model-Free Policy Iteration for Co-safe LTL Planning","created":"2026-08-05","cited_by_count":0,"area":"deeprl"},{"id":"2608.13625","title":"Reward Machines for Signal Temporal Logic","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.25968","title":"Quantitative Analysis of $\\omega$-Regular Robust MDPs","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.38065","title":"Jaxolotl: A Unified High-Performance Benchmark Suite for LTL-Based Multi-Task RL","created":"2026-09-29","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}