{"total":89,"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":"2206.09421","title":"Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation","created":"2022-06-19","cited_by_count":31,"area":null},{"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":"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":"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":"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":"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":"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":"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":"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":"2307.11044","title":"On the Convergence of Bounded Agents","created":"2023-07-20","cited_by_count":7,"area":null},{"id":"2510.01272","title":"Modeling Others' Minds as Code","created":"2025-09-29","cited_by_count":7,"area":null},{"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":"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":"2410.24080","title":"Graph Learning for Numeric Planning","created":"2024-10-31","cited_by_count":5,"area":null},{"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":"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":"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":"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":"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":"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":"2410.07923","title":"Deep Learning for Generalised Planning with Background Knowledge","created":"2024-10-10","cited_by_count":2,"area":null},{"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":"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},{"id":"2305.00508","title":"Learning Achievement Structure for Structured Exploration in Domains with Sparse Reward","created":"2023-04-30","cited_by_count":1,"area":null},{"id":"2305.04532","title":"Recent Trends in Artificial Intelligence Technology: A Scoping Review","created":"2023-05-08","cited_by_count":1,"area":null},{"id":"2307.05209","title":"Contextual Pre-planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning","created":"2023-07-11","cited_by_count":1,"area":null},{"id":"2308.04161","title":"Current and Future Challenges in Knowledge Representation and Reasoning","created":"2023-08-08","cited_by_count":1,"area":null},{"id":"2311.05084","title":"Signal Temporal Logic-Guided Apprenticeship Learning","created":"2023-11-09","cited_by_count":1,"area":null},{"id":"2311.09027","title":"Assessing the Robustness of Intelligence-Driven Reinforcement Learning","created":"2023-11-15","cited_by_count":1,"area":null},{"id":"2511.02304","title":"Automata-Conditioned Cooperative Multi-Agent Reinforcement Learning","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2603.11351","title":"Novelty Adaptation Through Hybrid Large Language Model (LLM)-Symbolic Planning and LLM-guided Reinforcement Learning","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2604.28056","title":"RHyVE: Competence-Aware Verification and Phase-Aware Deployment for LLM-Generated Reward Hypotheses","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2202.03188","title":"Knowledge-Integrated Informed AI for National Security","created":"2022-02-04","cited_by_count":0,"area":null},{"id":"2206.11430","title":"Recursive Reinforcement Learning","created":"2022-06-23","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":"2212.03733","title":"Tiered Reward: Designing Rewards for Specification and Fast Learning of Desired Behavior","created":"2022-12-07","cited_by_count":0,"area":null},{"id":"2307.00923","title":"Achieving Stable Training of Reinforcement Learning Agents in Bimodal Environments through Batch Learning","created":"2023-07-03","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":"2408.08059","title":"Maximally Permissive Reward Machines","created":"2024-08-15","cited_by_count":0,"area":null},{"id":"2408.10074","title":"Synthesis of Reward Machines for Multi-Agent Equilibrium Design (Full Version)","created":"2024-08-19","cited_by_count":0,"area":null},{"id":"2506.07829","title":"Decentralizing Multi-Agent Reinforcement Learning with Temporal Causal Information","created":"2025-06-09","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":"2604.07480","title":"Active Reward Machine Inference From Raw State Trajectories","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2605.27013","title":"Generating Robust Portfolios of Optimization Models using Large Language Models","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.21971","title":"REBA: A Revealed Belief Automaton Framework for Online Planning in Continuous POMDPs","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2608.13625","title":"Reward Machines for Signal Temporal Logic","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.24156","title":"LLM-Guided Contextual Action Evaluation for Operational Decisions in Industrial Processes","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.29490","title":"Generalizable Multi-Agent Planning from Signal Temporal Logic Specifications via Diffusion","created":"2026-08-30","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":"2609.19448","title":"The syntax and semantics of goals","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2610.01527","title":"Exact Distinguishability in Non-Markovian Decision Processes","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.20210","title":"Robust Counterfactuals for Markov Decision Processes under Statistical and Causal Uncertainties","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}