{"total":191,"rows":[{"id":"2102.06858","title":"LTL2Action: Generalizing LTL Instructions for Multi-Task RL","created":"2021-02-13","cited_by_count":74,"area":null},{"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":"2408.16984","title":"Beyond Preferences in AI Alignment","created":"2024-08-30","cited_by_count":49,"area":"alignment"},{"id":"2206.09421","title":"Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation","created":"2022-06-19","cited_by_count":31,"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":"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":"2405.01440","title":"A Review of Reward Functions for Reinforcement Learning in the context of Autonomous Driving","created":"2024-04-12","cited_by_count":18,"area":"driving"},{"id":"2112.09477","title":"Learning Reward Machines: A Study in Partially Observable Reinforcement Learning","created":"2021-12-17","cited_by_count":16,"area":null},{"id":"2310.19007","title":"Behavior Alignment via Reward Function Optimization","created":"2023-10-29","cited_by_count":16,"area":null},{"id":"2405.13242","title":"Goals as Reward-Producing Programs","created":"2024-05-21","cited_by_count":14,"area":null},{"id":"2407.10583","title":"Three Dogmas of Reinforcement Learning","created":"2024-07-15","cited_by_count":14,"area":"deeprl"},{"id":"2106.05864","title":"Verifiable and Compositional Reinforcement Learning Systems","created":"2021-06-07","cited_by_count":13,"area":null},{"id":"2107.04633","title":"Inferring Probabilistic Reward Machines from Non-Markovian Reward Processes for Reinforcement Learning","created":"2021-07-09","cited_by_count":13,"area":null},{"id":"2201.12231","title":"Overcoming Exploration: Deep Reinforcement Learning for Continuous Control in Cluttered Environments from Temporal Logic Specifications","created":"2022-01-28","cited_by_count":12,"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":"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":"2406.00120","title":"Reward Machines for Deep RL in Noisy and Uncertain Environments","created":"2024-05-31","cited_by_count":11,"area":"deeprl"},{"id":"2209.13220","title":"Exploiting Transformer in Sparse Reward Reinforcement Learning for Interpretable Temporal Logic Motion Planning","created":"2022-09-27","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":"2112.08438","title":"Programmatic Reward Design by Example","created":"2021-12-14","cited_by_count":9,"area":null},{"id":"2204.09772","title":"A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward Machines","created":"2022-04-20","cited_by_count":9,"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":"2205.12532","title":"Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning","created":"2022-05-25","cited_by_count":9,"area":null},{"id":"2401.14811","title":"On the Limitations of Markovian Rewards to Express Multi-Objective, Risk-Sensitive, and Modal Tasks","created":"2024-01-26","cited_by_count":9,"area":"deeprl"},{"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":"2312.04772","title":"Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Making","created":"2023-12-08","cited_by_count":8,"area":null},{"id":"2410.21795","title":"Robot Policy Learning with Temporal Optimal Transport Reward","created":"2024-10-29","cited_by_count":8,"area":"deeprl"},{"id":"2110.00096","title":"Decentralized Graph-Based Multi-Agent Reinforcement Learning Using Reward Machines","created":"2021-09-30","cited_by_count":7,"area":null},{"id":"2208.11838","title":"Learning Task Automata for Reinforcement Learning using Hidden Markov Models","created":"2022-08-25","cited_by_count":7,"area":null},{"id":"2210.15906","title":"Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences","created":"2022-10-28","cited_by_count":7,"area":"alignment"},{"id":"2307.11044","title":"On the Convergence of Bounded Agents","created":"2023-07-20","cited_by_count":7,"area":null},{"id":"2408.08677","title":"Neural Reward Machines","created":"2024-08-16","cited_by_count":7,"area":"deeprl"},{"id":"2408.09495","title":"Directed Exploration in Reinforcement Learning from Linear Temporal Logic","created":"2024-08-18","cited_by_count":7,"area":"deeprl"},{"id":"2408.14871","title":"Learning Robust Reward Machines from Noisy Labels","created":"2024-08-27","cited_by_count":7,"area":"deeprl"},{"id":"2510.01272","title":"Modeling Others' Minds as Code","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2510.14837","title":"Reinforcement Learning with Stochastic Reward Machines","created":"2025-10-16","cited_by_count":7,"area":"deeprl"},{"id":"2107.10969","title":"Learning Quadruped Locomotion Policies using Logical Rules","created":"2021-07-23","cited_by_count":6,"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":"2210.01162","title":"Learning Minimally-Violating Continuous Control for Infeasible Linear Temporal Logic Specifications","created":"2022-10-03","cited_by_count":6,"area":null},{"id":"2303.05038","title":"Exploiting Contextual Structure to Generate Useful Auxiliary Tasks","created":"2023-03-09","cited_by_count":6,"area":null},{"id":"2311.05490","title":"General Policies, Subgoal Structure, and Planning Width","created":"2023-11-09","cited_by_count":6,"area":null},{"id":"2312.11364","title":"Counting Reward Automata: Sample Efficient Reinforcement Learning Through the Exploitation of Reward Function Structure","created":"2023-12-18","cited_by_count":6,"area":null},{"id":"2410.23790","title":"Neural Model Checking","created":"2024-10-31","cited_by_count":6,"area":null},{"id":"2412.07207","title":"MAPLE: A Framework for Active Preference Learning Guided by Large Language Models","created":"2024-12-10","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":"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":"2401.11325","title":"Detecting Hidden Triggers: Mapping Non-Markov Reward Functions to Markov","created":"2024-01-20","cited_by_count":5,"area":"deeprl"},{"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":"2410.24080","title":"Graph Learning for Numeric Planning","created":"2024-10-31","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":"2510.01932","title":"Veri-R1: Toward Precise and Faithful Claim Verification via Online Reinforcement Learning","created":"2025-10-02","cited_by_count":5,"area":"lr"},{"id":"2510.14176","title":"ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement Learning","created":"2025-10-16","cited_by_count":5,"area":"deeprl"},{"id":"2602.06939","title":"Cochain Perspectives on Temporal-Difference Signals for Learning Beyond Markov Dynamics","created":"2026-02-06","cited_by_count":5,"area":null},{"id":"2203.12686","title":"Possibility Before Utility: Learning And Using Hierarchical Affordances","created":"2022-03-23","cited_by_count":4,"area":null},{"id":"2205.15752","title":"Hierarchies of Reward Machines","created":"2022-05-31","cited_by_count":4,"area":null},{"id":"2208.09570","title":"Calculus on MDPs: Potential Shaping as a Gradient","created":"2022-08-20","cited_by_count":4,"area":null},{"id":"2210.15096","title":"Towards customizable reinforcement learning agents: Enabling preference specification through online vocabulary expansion","created":"2022-10-27","cited_by_count":4,"area":null},{"id":"2310.19137","title":"Automaton Distillation: Neuro-Symbolic Transfer Learning for Deep Reinforcement Learning","created":"2023-10-29","cited_by_count":4,"area":null},{"id":"2403.15301","title":"Planning with a Learned Policy Basis to Optimally Solve Complex Tasks","created":"2024-03-22","cited_by_count":4,"area":"deeprl"},{"id":"2408.10381","title":"Efficient Reinforcement Learning in Probabilistic Reward Machines","created":"2024-08-19","cited_by_count":4,"area":"deeprl"},{"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":"2508.06894","title":"Pushdown Reward Machines for Reinforcement Learning","created":"2025-08-09","cited_by_count":4,"area":"deeprl"},{"id":"2206.13754","title":"DistSPECTRL: Distributing Specifications in Multi-Agent Reinforcement Learning Systems","created":"2022-06-28","cited_by_count":3,"area":null},{"id":"2309.06420","title":"Verifiable Reinforcement Learning Systems via Compositionality","created":"2023-09-09","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":"2402.14569","title":"Transformable Gaussian Reward Function for Socially-Aware Navigation with Deep Reinforcement Learning","created":"2024-02-22","cited_by_count":3,"area":"deeprl"},{"id":"2405.15908","title":"Knowledge-Informed Auto-Penetration Testing Based on Reinforcement Learning with Reward Machine","created":"2024-05-24","cited_by_count":3,"area":"deeprl"},{"id":"2408.02999","title":"LLMs as Probabilistic Minimally Adequate Teachers for DFA Learning","created":"2024-08-06","cited_by_count":3,"area":null},{"id":"2409.08904","title":"AnyBipe: An End-to-End Framework for Training and Deploying Bipedal Robots Guided by Large Language Models","created":"2024-09-13","cited_by_count":3,"area":null},{"id":"2411.10654","title":"Pluralistic Alignment Over Time","created":"2024-11-16","cited_by_count":3,"area":null},{"id":"2503.04931","title":"Curiosity-Driven Imagination: Discovering Plan Operators and Learning Associated Policies for Open-World Adaptation","created":"2025-03-06","cited_by_count":3,"area":"deeprl"},{"id":"2512.19154","title":"Beyond Sliding Windows: Learning to Manage Memory in Non-Markovian Environments","created":"2025-12-22","cited_by_count":3,"area":null},{"id":"2603.18859","title":"RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models","created":"2026-03-19","cited_by_count":3,"area":"lr"},{"id":"2203.00669","title":"Hierarchical Reinforcement Learning with AI Planning Models","created":"2022-03-01","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":"2303.14061","title":"Learning Reward Machines in Cooperative Multi-Agent Tasks","created":"2023-03-24","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":"2403.00832","title":"Explainable Session-based Recommendation via Path Reasoning","created":"2024-02-28","cited_by_count":2,"area":null},{"id":"2406.06460","title":"Towards Real-World Efficiency: Domain Randomization in Reinforcement Learning for Pre-Capture of Free-Floating Moving Targets by Autonomous Robots","created":"2024-06-10","cited_by_count":2,"area":"deeprl"},{"id":"2410.07923","title":"Deep Learning for Generalised Planning with Background Knowledge","created":"2024-10-10","cited_by_count":2,"area":null},{"id":"2503.23650","title":"A Survey of Reinforcement Learning-Based Motion Planning for Autonomous Driving: Lessons Learned from a Driving Task Perspective","created":"2025-03-31","cited_by_count":2,"area":"driving"},{"id":"2504.04675","title":"HypRL: Reinforcement Learning of Control Policies for Hyperproperties","created":"2025-04-07","cited_by_count":2,"area":"deeprl"},{"id":"2508.21501","title":"Few-Shot Neuro-Symbolic Imitation Learning for Long-Horizon Planning and Acting","created":"2025-08-29","cited_by_count":2,"area":"offlinerl"},{"id":"2509.20008","title":"Learning Robust Penetration Testing Policies under Partial Observability: A systematic evaluation","created":"2025-09-24","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":"2510.15456","title":"Expediting Reinforcement Learning by Incorporating Knowledge About Temporal Causality in the Environment","created":"2025-10-17","cited_by_count":2,"area":"deeprl"},{"id":"2601.22891","title":"PlatoLTL: Scaling LTL-Guided Multi-Task RL","created":"2026-01-30","cited_by_count":2,"area":"deeprl"},{"id":"2605.13077","title":"Counterfactual Reasoning for Causal Responsibility Attribution in Probabilistic Multi-Agent Systems","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2607.00442","title":"Learning Gait-Aware Quadruped Locomotion with Temporal Logic Specifications","created":"2026-07-01","cited_by_count":2,"area":"deeprl"},{"id":"2607.16506","title":"Foresight Residual RL for Long-Horizon Robot Manipulation with Vision-Language-Action Models","created":"2026-07-17","cited_by_count":2,"area":"vla"},{"id":"2205.08192","title":"Moral reinforcement learning using actual causation","created":"2022-05-17","cited_by_count":1,"area":null},{"id":"2212.04576","title":"Generalizing LTL Instructions via Future Dependent Options","created":"2022-12-08","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}],"next_cursor":"100"}