{"total":56,"rows":[{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73,"area":null},{"id":"2106.06235","title":"Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks","created":"2021-06-11","cited_by_count":24,"area":null},{"id":"2001.09227","title":"Active Task-Inference-Guided Deep Inverse Reinforcement Learning","created":"2020-01-24","cited_by_count":17,"area":"offlinerl"},{"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":"2112.09477","title":"Learning Reward Machines: A Study in Partially Observable Reinforcement Learning","created":"2021-12-17","cited_by_count":16,"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":"2212.01944","title":"Automaton-Based Representations of Task Knowledge from Generative Language Models","created":"2022-12-04","cited_by_count":12,"area":null},{"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":"2205.01053","title":"Markov Abstractions for PAC Reinforcement Learning in Non-Markov Decision Processes","created":"2022-04-29","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":"2212.01838","title":"Automata Learning meets Shielding","created":"2022-12-04","cited_by_count":9,"area":null},{"id":"2402.07069","title":"Using Large Language Models to Automate and Expedite Reinforcement Learning with Reward Machine","created":"2024-02-11","cited_by_count":9,"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":"2408.14871","title":"Learning Robust Reward Machines from Noisy Labels","created":"2024-08-27","cited_by_count":7,"area":"deeprl"},{"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":"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":"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":"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":"2205.15752","title":"Hierarchies of Reward Machines","created":"2022-05-31","cited_by_count":4,"area":null},{"id":"2206.11708","title":"Reinforcement Learning under Partial Observability Guided by Learned Environment Models","created":"2022-06-23","cited_by_count":4,"area":null},{"id":"2301.02952","title":"Learning Symbolic Representations for Reinforcement Learning of Non-Markovian Behavior","created":"2023-01-08","cited_by_count":4,"area":null},{"id":"2501.00364","title":"FORM: Learning Expressive and Transferable First-Order Logic Reward Machines","created":"2024-12-31","cited_by_count":4,"area":"deeprl"},{"id":"2105.11545","title":"Uncertainty-Aware Signal Temporal Logic Inference","created":"2021-05-24","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":"2409.02747","title":"Tractable Offline Learning of Regular Decision Processes","created":"2024-09-04","cited_by_count":3,"area":"offlinerl"},{"id":"2502.03762","title":"Learning Reward Machines from Partially Observed Policies","created":"2025-02-06","cited_by_count":3,"area":"offlinerl"},{"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":"2306.13732","title":"Reinforcement Learning with Temporal-Logic-Based Causal Diagrams","created":"2023-06-23","cited_by_count":2,"area":null},{"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":"2211.14028","title":"Automata Cascades: Expressivity and Sample Complexity","created":"2022-11-25","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":"2311.15960","title":"Program Machine Policy: Addressing Long-Horizon Tasks by Integrating Program Synthesis and State Machines","created":"2023-11-27","cited_by_count":1,"area":null},{"id":"2406.13991","title":"Bayesian Inverse Reinforcement Learning for Non-Markovian Rewards","created":"2024-06-20","cited_by_count":1,"area":"offlinerl"},{"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":"2209.13489","title":"Reward Learning using Structural Motifs in Inverse Reinforcement Learning","created":"2022-09-25","cited_by_count":0,"area":"offlinerl"},{"id":"2210.01955","title":"Learning Dynamic Abstract Representations for Sample-Efficient Reinforcement Learning","created":"2022-10-04","cited_by_count":0,"area":null},{"id":"2305.17372","title":"Reinforcement Learning With Reward Machines in Stochastic Games","created":"2023-05-27","cited_by_count":0,"area":null},{"id":"2306.17204","title":"Learning Environment Models with Continuous Stochastic Dynamics","created":"2023-06-29","cited_by_count":0,"area":null},{"id":"2401.14226","title":"Sample Efficient Reinforcement Learning by Automatically Learning to Compose Subtasks","created":"2024-01-25","cited_by_count":0,"area":"deeprl"},{"id":"2408.08059","title":"Maximally Permissive Reward Machines","created":"2024-08-15","cited_by_count":0,"area":null},{"id":"2505.15693","title":"Average Reward Reinforcement Learning for Omega-Regular and Mean-Payoff Objectives","created":"2025-05-21","cited_by_count":0,"area":"deeprl"},{"id":"2506.07829","title":"Decentralizing Multi-Agent Reinforcement Learning with Temporal Causal Information","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2508.14093","title":"Physics-Informed Reward Machines","created":"2025-08-14","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":"2603.03068","title":"Reinforcement Learning with Symbolic Reward Machines","created":"2026-03-03","cited_by_count":0,"area":"deeprl"},{"id":"2604.07480","title":"Active Reward Machine Inference From Raw State Trajectories","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2608.27797","title":"CEDAR: Automata as Verifiable Interfaces for Language-Guided Embodied Action","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.07461","title":"Temporal-Causal Inference for Reinforcement Learning via Automata Learning","created":"2026-09-07","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}