{"total":69,"rows":[{"id":"2102.06858","title":"LTL2Action: Generalizing LTL Instructions for Multi-Task RL","created":"2021-02-13","cited_by_count":74,"area":null},{"id":"2111.00876","title":"On the Expressivity of Markov Reward","created":"2021-11-01","cited_by_count":71,"area":null},{"id":"2106.13906","title":"Compositional Reinforcement Learning from Logical Specifications","created":"2021-06-25","cited_by_count":67,"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":"2207.07730","title":"How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition","created":"2022-07-15","cited_by_count":27,"area":null},{"id":"2102.12571","title":"The Logical Options Framework","created":"2021-02-24","cited_by_count":25,"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":"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":"2110.09461","title":"In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications","created":"2021-10-18","cited_by_count":17,"area":null},{"id":"2205.13728","title":"GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesis","created":"2022-05-27","cited_by_count":16,"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":"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":"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":"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":"2205.12532","title":"Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning","created":"2022-05-25","cited_by_count":9,"area":null},{"id":"2102.11137","title":"Program Synthesis Guided Reinforcement Learning for Partially Observed Environments","created":"2021-02-22","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":"2508.01561","title":"One Subgoal at a Time: Zero-Shot Generalization to Arbitrary Linear Temporal Logic Requirements in Multi-Task Reinforcement Learning","created":"2025-08-03","cited_by_count":8,"area":"deeprl"},{"id":"2510.14837","title":"Reinforcement Learning with Stochastic Reward Machines","created":"2025-10-16","cited_by_count":7,"area":"deeprl"},{"id":"2202.02404","title":"Model-Free Reinforcement Learning for Symbolic Automata-encoded Objectives","created":"2022-02-04","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":"2510.00225","title":"TGPO: Temporal Grounded Policy Optimization for Signal Temporal Logic Tasks","created":"2025-09-30","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":"2207.04117","title":"Ablation Study of How Run Time Assurance Impacts the Training and Performance of Reinforcement Learning Agents","created":"2022-07-08","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":"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":"2205.15752","title":"Hierarchies of Reward Machines","created":"2022-05-31","cited_by_count":4,"area":null},{"id":"2208.06448","title":"RLang: A Declarative Language for Describing Partial World Knowledge to Reinforcement Learning Agents","created":"2022-08-12","cited_by_count":4,"area":null},{"id":"2506.22365","title":"Reinforcement Learning with Physics-Informed Symbolic Program Priors for Zero-Shot Wireless Indoor Navigation","created":"2025-06-27","cited_by_count":4,"area":"deeprl"},{"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":"2402.03678","title":"Logical Specifications-guided Dynamic Task Sampling for Reinforcement Learning Agents","created":"2024-02-06","cited_by_count":3,"area":"deeprl"},{"id":"2402.07019","title":"Informativeness of Reward Functions in Reinforcement Learning","created":"2024-02-10","cited_by_count":3,"area":"deeprl"},{"id":"2403.07005","title":"Multi-Agent Reinforcement Learning with a Hierarchy of Reward Machines","created":"2024-03-08","cited_by_count":3,"area":null},{"id":"2406.03651","title":"Inductive Generalization in Reinforcement Learning from Specifications","created":"2024-06-05","cited_by_count":3,"area":"deeprl"},{"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":"2307.14465","title":"What Kinds of Contracts Do ML APIs Need?","created":"2023-07-26","cited_by_count":2,"area":null},{"id":"2412.10915","title":"Canopy: Property-Driven Learning for Congestion Control","created":"2024-12-14","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":"2601.22891","title":"PlatoLTL: Scaling LTL-Guided Multi-Task RL","created":"2026-01-30","cited_by_count":2,"area":"deeprl"},{"id":"2111.03647","title":"Regular Decision Processes for Grid Worlds","created":"2021-11-05","cited_by_count":1,"area":null},{"id":"2306.08916","title":"Counterfactuals Modulo Temporal Logics","created":"2023-06-15","cited_by_count":1,"area":null},{"id":"2404.19370","title":"Numeric Reward Machines","created":"2024-04-30","cited_by_count":1,"area":"deeprl"},{"id":"2410.09686","title":"Generalization of Compositional Tasks with Logical Specification via Implicit Planning","created":"2024-10-13","cited_by_count":1,"area":"deeprl"},{"id":"2501.18848","title":"Reinforcement Learning of Flexible Policies for Symbolic Instructions with Adjustable Mapping Specifications","created":"2025-01-31","cited_by_count":1,"area":"deeprl"},{"id":"2511.02304","title":"Automata-Conditioned Cooperative Multi-Agent Reinforcement Learning","created":"2025-11-04","cited_by_count":1,"area":null},{"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":"2107.10390","title":"Reinforcement Learning Agent Training with Goals for Real World Tasks","created":"2021-07-21","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":"2306.17033","title":"Safety-Aware Task Composition for Discrete and Continuous Reinforcement Learning","created":"2023-06-29","cited_by_count":0,"area":null},{"id":"2402.15826","title":"Reward Design for Justifiable Sequential Decision-Making","created":"2024-02-24","cited_by_count":0,"area":"alignment"},{"id":"2410.24096","title":"Progressive Safeguards for Safe and Model-Agnostic Reinforcement Learning","created":"2024-10-31","cited_by_count":0,"area":"deeprl"},{"id":"2412.16970","title":"A Research Agenda for Usability and Generalisation in Reinforcement Learning","created":"2024-12-22","cited_by_count":0,"area":"deeprl"},{"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":"2510.15728","title":"RLAF: Reinforcement Learning from Automaton Feedback","created":"2025-10-17","cited_by_count":0,"area":"alignment"},{"id":"2510.16185","title":"Expressive Reward Synthesis with the Runtime Monitoring Language","created":"2025-10-17","cited_by_count":0,"area":"deeprl"},{"id":"2510.27329","title":"Reinforcement Learning for Long-Horizon Unordered Tasks: From Boolean to Coupled Reward Machines","created":"2025-10-31","cited_by_count":0,"area":"deeprl"},{"id":"2511.12808","title":"Expressive Temporal Specifications for Reward Monitoring","created":"2025-11-16","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":"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":"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":"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":"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}