{"total":67,"rows":[{"id":"2102.06858","title":"LTL2Action: Generalizing LTL Instructions for Multi-Task RL","created":"2021-02-13","cited_by_count":74,"area":null},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"area":null},{"id":"2106.13906","title":"Compositional Reinforcement Learning from Logical Specifications","created":"2021-06-25","cited_by_count":67,"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":"2205.06750","title":"Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarking","created":"2022-05-13","cited_by_count":34,"area":null},{"id":"2109.10294","title":"DeepSTL -- From English Requirements to Signal Temporal Logic","created":"2021-09-21","cited_by_count":22,"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":"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":"2102.07730","title":"Learning from Demonstrations using Signal Temporal Logic","created":"2021-02-15","cited_by_count":17,"area":"offlinerl"},{"id":"2305.17115","title":"Policy Synthesis and Reinforcement Learning for Discounted LTL","created":"2023-05-26","cited_by_count":14,"area":null},{"id":"2309.05131","title":"Signal Temporal Logic Neural Predictive Control","created":"2023-09-10","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":"2404.11578","title":"LTL-Constrained Policy Optimization with Cycle Experience Replay","created":"2024-04-17","cited_by_count":11,"area":"deeprl"},{"id":"2406.00120","title":"Reward Machines for Deep RL in Noisy and Uncertain Environments","created":"2024-05-31","cited_by_count":11,"area":"deeprl"},{"id":"2109.13377","title":"Model-Free Reinforcement Learning for Optimal Control of MarkovDecision Processes Under Signal Temporal Logic Specifications","created":"2021-09-27","cited_by_count":10,"area":null},{"id":"2211.10902","title":"Noisy Symbolic Abstractions for Deep RL: A case study with Reward Machines","created":"2022-11-20","cited_by_count":10,"area":null},{"id":"2201.08504","title":"Deep reinforcement learning under signal temporal logic constraints using Lagrangian relaxation","created":"2022-01-21","cited_by_count":8,"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":"2212.03181","title":"Funnel-based Reward Shaping for Signal Temporal Logic Tasks in Reinforcement Learning","created":"2022-11-30","cited_by_count":8,"area":null},{"id":"2202.02404","title":"Model-Free Reinforcement Learning for Symbolic Automata-encoded Objectives","created":"2022-02-04","cited_by_count":6,"area":null},{"id":"2304.06160","title":"Learning Robust and Correct Controllers from Signal Temporal Logic Specifications Using BarrierNet","created":"2023-04-12","cited_by_count":6,"area":null},{"id":"2501.13457","title":"Zero-Shot Trajectory Planning for Signal Temporal Logic Tasks","created":"2025-01-23","cited_by_count":6,"area":null},{"id":"2510.00225","title":"TGPO: Temporal Grounded Policy Optimization for Signal Temporal Logic Tasks","created":"2025-09-30","cited_by_count":6,"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":"2507.10741","title":"Ground-Compose-Reinforce: Grounding Language in Agentic Behaviours using Limited Data","created":"2025-07-14","cited_by_count":5,"area":"agents"},{"id":"2408.05336","title":"Logically Constrained Robotics Transformers for Enhanced Perception-Action Planning","created":"2024-08-09","cited_by_count":4,"area":null},{"id":"2103.15938","title":"Safe Model-based Control from Signal Temporal Logic Specifications Using Recurrent Neural Networks","created":"2021-03-29","cited_by_count":3,"area":null},{"id":"2107.12942","title":"Reinforcement Learning with Formal Performance Metrics for Quadcopter Attitude Control under Non-nominal Contexts","created":"2021-07-27","cited_by_count":3,"area":null},{"id":"2204.05909","title":"Learning Performance Graphs from Demonstrations via Task-Based Evaluations","created":"2022-04-12","cited_by_count":3,"area":"offlinerl"},{"id":"2402.10310","title":"Interpretable Imitation Learning via Generative Adversarial STL Inference and Control","created":"2024-02-15","cited_by_count":3,"area":"offlinerl"},{"id":"2406.03651","title":"Inductive Generalization in Reinforcement Learning from Specifications","created":"2024-06-05","cited_by_count":3,"area":"deeprl"},{"id":"2503.02012","title":"Pretrained Embeddings as a Behavior Specification Mechanism","created":"2025-03-03","cited_by_count":3,"area":null},{"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":"2306.13732","title":"Reinforcement Learning with Temporal-Logic-Based Causal Diagrams","created":"2023-06-23","cited_by_count":2,"area":null},{"id":"2504.04675","title":"HypRL: Reinforcement Learning of Control Policies for Hyperproperties","created":"2025-04-07","cited_by_count":2,"area":"deeprl"},{"id":"2510.05061","title":"Automaton Constrained Q-Learning","created":"2025-10-06","cited_by_count":2,"area":"deeprl"},{"id":"2607.00442","title":"Learning Gait-Aware Quadruped Locomotion with Temporal Logic Specifications","created":"2026-07-01","cited_by_count":2,"area":"deeprl"},{"id":"2101.10404","title":"Learning-'N-Flying: A Learning-based, Decentralized Mission Aware UAS Collision Avoidance Scheme","created":"2021-01-25","cited_by_count":1,"area":null},{"id":"2108.01317","title":"Deep Reinforcement Learning Based Networked Control with Network Delays for Signal Temporal Logic Specifications","created":"2021-08-03","cited_by_count":1,"area":null},{"id":"2111.08733","title":"Learning Provably Robust Motion Planners Using Funnel Libraries","created":"2021-11-16","cited_by_count":1,"area":null},{"id":"2210.07439","title":"Risk-Awareness in Learning Neural Controllers for Temporal Logic Objectives","created":"2022-10-14","cited_by_count":1,"area":null},{"id":"2212.05200","title":"Neural Controller Synthesis for Signal Temporal Logic Specifications Using Encoder-Decoder Structured Networks","created":"2022-12-10","cited_by_count":1,"area":null},{"id":"2403.15916","title":"Multi-agent transformer-accelerated RL for satisfaction of STL specifications","created":"2024-03-23","cited_by_count":1,"area":null},{"id":"2410.08022","title":"Probabilistic Satisfaction of Temporal Logic Constraints in Reinforcement Learning via Adaptive Policy-Switching","created":"2024-10-10","cited_by_count":1,"area":"deeprl"},{"id":"2411.17861","title":"Accelerating Proximal Policy Optimization Learning Using Task Prediction for Solving Environments with Delayed Rewards","created":"2024-11-26","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":"2603.17152","title":"Shielded Reinforcement Learning Under Dynamic Temporal Logic Constraints","created":"2026-03-17","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":"2605.12651","title":"Runtime Monitoring of Perception-Based Autonomous Systems via Embedding Temporal Logic","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2212.11792","title":"CatlNet: Learning Communication and Coordination Policies from CaTL+ Specifications","created":"2022-11-30","cited_by_count":0,"area":null},{"id":"2503.05818","title":"Closing the Intent-to-Behavior Gap via Fulfillment Priority Logic","created":"2025-03-04","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":"2510.16185","title":"Expressive Reward Synthesis with the Runtime Monitoring Language","created":"2025-10-17","cited_by_count":0,"area":"deeprl"},{"id":"2512.01047","title":"Automating the Refinement of Reinforcement Learning Specifications","created":"2025-11-30","cited_by_count":0,"area":"deeprl"},{"id":"2512.06973","title":"Feasibility-aware Learning of Robust Temporal Logic Controllers using BarrierNet","created":"2025-12-07","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":"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":"2603.17969","title":"Specification-Aware Distribution Shaping for Robotics Foundation Models","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2604.04225","title":"Learning from Imperfect Demonstrations via Temporal Behavior Tree-Guided Trajectory Repair","created":"2026-04-05","cited_by_count":0,"area":"deeprl"},{"id":"2604.14440","title":"On Tackling Complex Tasks with Reward Machines and Signal Temporal Logics","created":"2026-04-09","cited_by_count":0,"area":"deeprl"},{"id":"2605.01222","title":"Zero-Shot Signal Temporal Logic Planning with Disjunctive Branch Selection in Dynamic Semantic Maps","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2605.24740","title":"Reinforcement Learning for Reachability: Guaranteeing Asymptotic Optimality","created":"2026-05-23","cited_by_count":0,"area":"deeprl"},{"id":"2606.00838","title":"Decoupled Behavioral Cloning for Scalable Inductive Generalization in RL from Specifications","created":"2026-05-30","cited_by_count":0,"area":"offlinerl"},{"id":"2608.13625","title":"Reward Machines for Signal Temporal Logic","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2609.07111","title":"From LLM-Generated Specifications to Learned Quadruped Locomotion","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.28396","title":"Tractable Reinforcement Learning for Full Class of Signal Temporal Logic Specifications Using Spatiotemporal Tube Reward","created":"2026-09-23","cited_by_count":0,"area":"deeprl"},{"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}