{"total":117,"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":"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":"2205.06750","title":"Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarking","created":"2022-05-13","cited_by_count":34,"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":"2102.12571","title":"The Logical Options Framework","created":"2021-02-24","cited_by_count":25,"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":"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":"2102.07730","title":"Learning from Demonstrations using Signal Temporal Logic","created":"2021-02-15","cited_by_count":17,"area":"offlinerl"},{"id":"2506.01622","title":"General agents contain world models","created":"2025-06-02","cited_by_count":17,"area":"wm"},{"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":"2407.10583","title":"Three Dogmas of Reinforcement Learning","created":"2024-07-15","cited_by_count":14,"area":"deeprl"},{"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":"2101.11981","title":"Embedding Symbolic Temporal Knowledge into Deep Sequential Models","created":"2021-01-28","cited_by_count":11,"area":"offlinerl"},{"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":"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":"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":"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":"2205.12532","title":"Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning","created":"2022-05-25","cited_by_count":9,"area":null},{"id":"2505.00562","title":"TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching","created":"2025-05-01","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":"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":"2503.02924","title":"Diverse Controllable Diffusion Policy with Signal Temporal Logic","created":"2025-03-04","cited_by_count":8,"area":"diffusion"},{"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":"2110.02792","title":"Hierarchical Potential-based Reward Shaping from Task Specifications","created":"2021-10-06","cited_by_count":7,"area":null},{"id":"2306.06808","title":"Multi-Agent Reinforcement Learning Guided by Signal Temporal Logic Specifications","created":"2023-06-11","cited_by_count":7,"area":null},{"id":"2405.00871","title":"Learning to Boost the Performance of Stable Nonlinear Systems","created":"2024-05-01","cited_by_count":7,"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":"2202.02404","title":"Model-Free Reinforcement Learning for Symbolic Automata-encoded Objectives","created":"2022-02-04","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":"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":"2103.14600","title":"Model-Free Learning of Safe yet Effective Controllers","created":"2021-03-26","cited_by_count":5,"area":null},{"id":"2111.04147","title":"Learning Finite Linear Temporal Logic Specifications with a Specialized Neural Operator","created":"2021-11-07","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":"2401.11325","title":"Detecting Hidden Triggers: Mapping Non-Markov Reward Functions to Markov","created":"2024-01-20","cited_by_count":5,"area":"deeprl"},{"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":"2203.12686","title":"Possibility Before Utility: Learning And Using Hierarchical Affordances","created":"2022-03-23","cited_by_count":4,"area":null},{"id":"2408.10381","title":"Efficient Reinforcement Learning in Probabilistic Reward Machines","created":"2024-08-19","cited_by_count":4,"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":"2103.12558","title":"Assured Learning-enabled Autonomy: A Metacognitive Reinforcement Learning Framework","created":"2021-03-23","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":"2403.07005","title":"Multi-Agent Reinforcement Learning with a Hierarchy of Reward Machines","created":"2024-03-08","cited_by_count":3,"area":null},{"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":"2406.03651","title":"Inductive Generalization in Reinforcement Learning from Specifications","created":"2024-06-05","cited_by_count":3,"area":"deeprl"},{"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":"2506.16016","title":"Dual-Objective Reinforcement Learning with Novel Hamilton-Jacobi-Bellman Formulations","created":"2025-06-19","cited_by_count":3,"area":"deeprl"},{"id":"2203.04172","title":"Distributed Control using Reinforcement Learning with Temporal-Logic-Based Reward Shaping","created":"2022-03-08","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":"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":"2505.12107","title":"Learning Probabilistic Temporal Logic Specifications for Stochastic Systems","created":"2025-05-17","cited_by_count":2,"area":null},{"id":"2510.05061","title":"Automaton Constrained Q-Learning","created":"2025-10-06","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":"2607.00442","title":"Learning Gait-Aware Quadruped Locomotion with Temporal Logic Specifications","created":"2026-07-01","cited_by_count":2,"area":"deeprl"},{"id":"2607.18580","title":"STeP: Signal Temporal Logic for Precise Specifications for Action Generation with Vision Language Models","created":"2026-07-20","cited_by_count":2,"area":"mllm"},{"id":"2107.02912","title":"Supervised Bayesian Specification Inference from Demonstrations","created":"2021-07-06","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":"2111.03647","title":"Regular Decision Processes for Grid Worlds","created":"2021-11-05","cited_by_count":1,"area":null},{"id":"2210.01344","title":"Movement Analytics: Current Status, Application to Manufacturing, and Future Prospects from an AI Perspective","created":"2022-10-04","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":"2303.09528","title":"Reinforcement Learning for Omega-Regular Specifications on Continuous-Time MDP","created":"2023-03-16","cited_by_count":1,"area":null},{"id":"2305.16505","title":"Reward-Machine-Guided, Self-Paced Reinforcement Learning","created":"2023-05-25","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":"2309.16960","title":"On Generating Explanations for Reinforcement Learning Policies: An Empirical Study","created":"2023-09-29","cited_by_count":1,"area":null},{"id":"2402.15893","title":"Concurrent Learning of Policy and Unknown Safety Constraints in Reinforcement Learning","created":"2024-02-24","cited_by_count":1,"area":"deeprl"},{"id":"2404.19370","title":"Numeric Reward Machines","created":"2024-04-30","cited_by_count":1,"area":"deeprl"},{"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":"2603.29868","title":"Spatiotemporal Robustness of Temporal Logic Tasks using Multi-Objective Reasoning","created":"2026-01-28","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":"2210.11259","title":"Safe Policy Improvement in Constrained Markov Decision Processes","created":"2022-10-20","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":"2302.14509","title":"Policy Dispersion in Non-Markovian Environment","created":"2023-02-28","cited_by_count":0,"area":null},{"id":"2304.03104","title":"Constrained Exploration in Reinforcement Learning with Optimality Preservation","created":"2023-04-05","cited_by_count":0,"area":null},{"id":"2304.12508","title":"Fulfilling Formal Specifications ASAP by Model-free Reinforcement Learning","created":"2023-04-25","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":"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":"2408.04215","title":"Comp-LTL: Temporal Logic Planning via Zero-Shot Policy Composition","created":"2024-08-08","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":"2506.09499","title":"A Unified Theory of Compositionality, Modularity, and Interpretability in Markov Decision Processes","created":"2025-06-11","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":"2510.15728","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":"2603.02396","title":"COOL-MC: Verifying and Explaining RL Policies for Platelet Inventory Management","created":"2026-03-02","cited_by_count":0,"area":null}],"next_cursor":"100"}