{"total":94,"rows":[{"id":"2401.05821","title":"Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents","created":"2024-01-11","cited_by_count":23,"area":"deeprl"},{"id":"2410.20018","title":"GHIL-Glue: Hierarchical Control with Filtered Subgoal Images","created":"2024-10-26","cited_by_count":15,"area":"deeprl"},{"id":"2406.17768","title":"EXTRACT: Efficient Policy Learning by Extracting Transferable Robot Skills from Offline Data","created":"2024-06-25","cited_by_count":13,"area":"deeprl"},{"id":"2406.03997","title":"HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning","created":"2024-06-06","cited_by_count":11,"area":"deeprl"},{"id":"2411.12155","title":"Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learning","created":"2024-11-19","cited_by_count":10,"area":"deeprl"},{"id":"2403.13281","title":"Waypoint-Based Reinforcement Learning for Robot Manipulation Tasks","created":"2024-03-20","cited_by_count":9,"area":"deeprl"},{"id":"2506.09366","title":"SkillBlender: Towards Versatile Humanoid Whole-Body Loco-Manipulation via Skill Blending","created":"2025-06-11","cited_by_count":9,"area":"deeprl"},{"id":"2411.00230","title":"Reinforcement learning with learned gadgets to tackle hard quantum problems on real hardware","created":"2024-10-31","cited_by_count":7,"area":"deeprl"},{"id":"2412.14355","title":"Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference","created":"2024-12-18","cited_by_count":7,"area":"deeprl"},{"id":"2505.19053","title":"Structured Reinforcement Learning for Combinatorial Decision-Making","created":"2025-05-25","cited_by_count":7,"area":"deeprl"},{"id":"2506.04147","title":"SLAC: Safe and Efficient Real-Robot Reinforcement Learning via Unsupervised Simulation Pre-Training","created":"2025-06-04","cited_by_count":7,"area":"deeprl"},{"id":"2407.06121","title":"Periodic agent-state based Q-learning for POMDPs","created":"2024-07-08","cited_by_count":6,"area":"deeprl"},{"id":"2509.22442","title":"Learning to Ball: Composing Policies for Long-Horizon Basketball Moves","created":"2025-09-26","cited_by_count":6,"area":"deeprl"},{"id":"2405.15920","title":"SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning","created":"2024-05-24","cited_by_count":5,"area":"deeprl"},{"id":"2502.03752","title":"Self-Improving Skill Learning for Robust Skill-based Meta-Reinforcement Learning","created":"2025-02-06","cited_by_count":5,"area":"deeprl"},{"id":"2509.00338","title":"Scalable Option Learning in High-Throughput Environments","created":"2025-08-30","cited_by_count":5,"area":"deeprl"},{"id":"2412.16395","title":"Autonomous Option Invention for Continual Hierarchical Reinforcement Learning and Planning","created":"2024-12-20","cited_by_count":4,"area":"deeprl"},{"id":"2512.00085","title":"Hyper-GoalNet: Goal-Conditioned Manipulation Policy Learning with HyperNetworks","created":"2025-11-26","cited_by_count":4,"area":"deeprl"},{"id":"2402.05439","title":"Learning Uncertainty-Aware Temporally-Extended Actions","created":"2024-02-08","cited_by_count":3,"area":"deeprl"},{"id":"2504.14805","title":"Dynamic Contrastive Skill Learning with State-Transition Based Skill Clustering and Dynamic Length Adjustment","created":"2025-04-21","cited_by_count":3,"area":"deeprl"},{"id":"2406.07897","title":"When Do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal Abstractions","created":"2024-06-12","cited_by_count":2,"area":"deeprl"},{"id":"2406.17168","title":"Reinforcement Learning via Auxiliary Task Distillation","created":"2024-06-24","cited_by_count":2,"area":"deeprl"},{"id":"2410.00704","title":"Contrastive Abstraction for Reinforcement Learning","created":"2024-10-01","cited_by_count":2,"area":"deeprl"},{"id":"2502.16634","title":"OptionZero: Planning with Learned Options","created":"2025-02-23","cited_by_count":2,"area":"deeprl"},{"id":"2503.14973","title":"Behaviour Discovery and Attribution for Explainable Reinforcement Learning","created":"2025-03-19","cited_by_count":2,"area":"deeprl"},{"id":"2505.12508","title":"InnateCoder: Learning Programmatic Options with Foundation Models","created":"2025-05-18","cited_by_count":2,"area":"deeprl"},{"id":"2506.18126","title":"Decentralized Consensus Inference-based Hierarchical Reinforcement Learning for Multi-Constrained UAV Pursuit-Evasion Game","created":"2025-06-22","cited_by_count":2,"area":"deeprl"},{"id":"2605.03434","title":"Quantum Hierarchical Reinforcement Learning via Variational Quantum Circuits","created":"2026-05-05","cited_by_count":2,"area":"deeprl"},{"id":"2402.13219","title":"Analyzing Operator States and the Impact of AI-Enhanced Decision Support in Control Rooms: A Human-in-the-Loop Specialized Reinforcement Learning Framework for Intervention Strategies","created":"2024-02-20","cited_by_count":1,"area":"deeprl"},{"id":"2407.18913","title":"SOAP-RL: Sequential Option Advantage Propagation for Reinforcement Learning in POMDP Environments","created":"2024-07-26","cited_by_count":1,"area":"deeprl"},{"id":"2409.07416","title":"Hierarchical Reinforcement Learning for Temporal Abstraction of Listwise Recommendation","created":"2024-09-11","cited_by_count":1,"area":"deeprl"},{"id":"2410.23419","title":"Stepping Out of the Shadows: Reinforcement Learning in Shadow Mode","created":"2024-10-30","cited_by_count":1,"area":"deeprl"},{"id":"2412.16687","title":"Subgoal Discovery Using a Free Energy Paradigm and State Aggregations","created":"2024-12-21","cited_by_count":1,"area":"deeprl"},{"id":"2501.02221","title":"CORD: Generalizable Cooperation via Role Diversity","created":"2025-01-04","cited_by_count":1,"area":"deeprl"},{"id":"2503.12688","title":"Dynamic Angle Selection in X-Ray CT: A Reinforcement Learning Approach to Optimal Stopping","created":"2025-03-16","cited_by_count":1,"area":"deeprl"},{"id":"2504.04366","title":"Solving Sokoban using Hierarchical Reinforcement Learning with Landmarks","created":"2025-04-06","cited_by_count":1,"area":"deeprl"},{"id":"2504.18794","title":"Hierarchical Reinforcement Learning in Multi-Goal Spatial Navigation with Autonomous Mobile Robots","created":"2025-04-26","cited_by_count":1,"area":"deeprl"},{"id":"2505.01979","title":"D3HRL: A Distributed Hierarchical Reinforcement Learning Approach Based on Causal Discovery and Spurious Correlation Detection","created":"2025-05-04","cited_by_count":1,"area":"deeprl"},{"id":"2505.10262","title":"Electric Bus Charging Schedules Relying on Real Data-Driven Targets Based on Hierarchical Deep Reinforcement Learning","created":"2025-05-15","cited_by_count":1,"area":"deeprl"},{"id":"2505.10296","title":"Optimizing Electric Bus Charging Scheduling with Uncertainties Using Hierarchical Deep Reinforcement Learning","created":"2025-05-15","cited_by_count":1,"area":"deeprl"},{"id":"2506.21039","title":"Strict Subgoal Execution: Reliable Long-Horizon Planning in Hierarchical Reinforcement Learning","created":"2025-06-26","cited_by_count":1,"area":"deeprl"},{"id":"2512.14617","title":"Model-Based Reinforcement Learning in Discrete-Action Non-Markovian Reward Decision Processes","created":"2025-12-16","cited_by_count":1,"area":"deeprl"},{"id":"2602.02532","title":"CADENT: Gated Hybrid Distillation for Sample-Efficient Transfer in Reinforcement Learning","created":"2026-01-28","cited_by_count":1,"area":"deeprl"},{"id":"2603.12543","title":"CALF: Communication-Aware Learning Framework for Distributed Reinforcement Learning","created":"2026-03-13","cited_by_count":1,"area":"deeprl"},{"id":"2604.11214","title":"HiEdit: Lifelong Model Editing with Hierarchical Reinforcement Learning","created":"2026-04-13","cited_by_count":1,"area":"deeprl"},{"id":"2605.06149","title":"AdaGamma: State-Dependent Discounting for Temporal Adaptation in Reinforcement Learning","created":"2026-05-07","cited_by_count":1,"area":"deeprl"},{"id":"2401.01993","title":"On Time-Indexing as Inductive Bias in Deep RL for Sequential Manipulation Tasks","created":"2024-01-03","cited_by_count":0,"area":"deeprl"},{"id":"2405.15829","title":"Spatio-temporal Value Semantics-based Abstraction for Dense Deep Reinforcement Learning","created":"2024-05-24","cited_by_count":0,"area":"deeprl"},{"id":"2406.18053","title":"Bidirectional-Reachable Hierarchical Reinforcement Learning with Mutually Responsive Policies","created":"2024-06-26","cited_by_count":0,"area":"deeprl"},{"id":"2410.07921","title":"Boosting Hierarchical Reinforcement Learning with Meta-Learning for Complex Task Adaptation","created":"2024-10-10","cited_by_count":0,"area":"deeprl"},{"id":"2410.11262","title":"Unveiling Options with Neural Decomposition","created":"2024-10-15","cited_by_count":0,"area":"deeprl"},{"id":"2411.02998","title":"Accelerating Task Generalisation with Multi-Level Skill Hierarchies","created":"2024-11-05","cited_by_count":0,"area":"deeprl"},{"id":"2501.06554","title":"Hierarchical Reinforcement Learning for Optimal Agent Grouping in Cooperative Systems","created":"2025-01-11","cited_by_count":0,"area":"deeprl"},{"id":"2502.06919","title":"Select before Act: Spatially Decoupled Action Repetition for Continuous Control","created":"2025-02-10","cited_by_count":0,"area":"deeprl"},{"id":"2503.00227","title":"The Learning Approach to Games","created":"2025-02-28","cited_by_count":0,"area":"deeprl"},{"id":"2503.13414","title":"Provably Efficient Reward Transfer in Reinforcement Learning with Discrete Markov Decision Processes","created":"2025-03-17","cited_by_count":0,"area":"deeprl"},{"id":"2503.14809","title":"Learning with Expert Abstractions for Efficient Multi-Task Continuous Control","created":"2025-03-19","cited_by_count":0,"area":"deeprl"},{"id":"2503.21677","title":"A tale of two goals: leveraging sequentiality in multi-goal scenarios","created":"2025-03-27","cited_by_count":0,"area":"deeprl"},{"id":"2505.21410","title":"MRS: Multi-Resolution Skills for HRL Agents","created":"2025-05-27","cited_by_count":0,"area":"deeprl"},{"id":"2506.02050","title":"Decoupled Hierarchical Reinforcement Learning with State Abstraction for Discrete Grids","created":"2025-06-01","cited_by_count":0,"area":"deeprl"},{"id":"2506.14391","title":"HALO: Hierarchical Reinforcement Learning for Large-Scale Adaptive Traffic Signal Control","created":"2025-06-17","cited_by_count":0,"area":"deeprl"},{"id":"2507.04373","title":"Hierarchical Reinforcement Learning with Targeted Causal Interventions","created":"2025-07-06","cited_by_count":0,"area":"deeprl"},{"id":"2508.13922","title":"Categorical Policies: Multimodal Policy Learning and Exploration in Continuous Control","created":"2025-08-19","cited_by_count":0,"area":"deeprl"},{"id":"2508.20102","title":"A Hierarchical Signal Coordination and Control System Using a Hybrid Model-based and Reinforcement Learning Approach","created":"2025-08-12","cited_by_count":0,"area":"deeprl"},{"id":"2510.24674","title":"Learning to Drive Safely with Hybrid Options","created":"2025-10-28","cited_by_count":0,"area":"deeprl"},{"id":"2510.24988","title":"Enhancing Hierarchical Reinforcement Learning through Change Point Detection in Time Series","created":"2025-10-28","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":"2511.12361","title":"SAC-MoE: Reinforcement Learning with Mixture-of-Experts for Control of Hybrid Dynamical Systems with Uncertainty","created":"2025-11-15","cited_by_count":0,"area":"deeprl"},{"id":"2511.17351","title":"Convergence and stability of Q-learning in Hierarchical Reinforcement Learning","created":"2025-11-21","cited_by_count":0,"area":"deeprl"},{"id":"2512.04958","title":"Realizable Abstractions: Near-Optimal Hierarchical Reinforcement Learning","created":"2025-12-04","cited_by_count":0,"area":"deeprl"},{"id":"2601.23156","title":"Unsupervised Hierarchical Skill Discovery","created":"2026-01-30","cited_by_count":0,"area":"deeprl"},{"id":"2602.13865","title":"Enabling Option Learning in Sparse Rewards with Hindsight Experience Replay","created":"2026-02-14","cited_by_count":0,"area":"deeprl"},{"id":"2603.06565","title":"Boosting deep Reinforcement Learning using pretraining with Logical Options","created":"2026-03-06","cited_by_count":0,"area":"deeprl"},{"id":"2604.07016","title":"Predictive Representations for Skill Transfer in Reinforcement Learning","created":"2026-04-08","cited_by_count":0,"area":"deeprl"},{"id":"2604.13133","title":"Automated co-design of high-performance thermodynamic cycles via graph-based hierarchical reinforcement learning","created":"2026-04-14","cited_by_count":0,"area":"deeprl"},{"id":"2604.24558","title":"Hierarchical Behaviour Spaces","created":"2026-04-27","cited_by_count":0,"area":"deeprl"},{"id":"2605.12261","title":"Delay-Empowered Causal Hierarchical Reinforcement Learning","created":"2026-05-12","cited_by_count":0,"area":"deeprl"},{"id":"2605.13207","title":"Switching Successor Measures for Hierarchical Zero-shot Reinforcement Learning","created":"2026-05-13","cited_by_count":0,"area":"deeprl"},{"id":"2605.23551","title":"Goal-Conditioned Agents that Learn Everything All at Once","created":"2026-05-22","cited_by_count":0,"area":"deeprl"},{"id":"2605.24343","title":"Adaptive Human-AI Coordination via Hierarchical Action Disentanglement","created":"2026-05-23","cited_by_count":0,"area":"deeprl"},{"id":"2606.00880","title":"Task diversity produces systematic transfer but inhibits continual reinforcement learning","created":"2026-05-30","cited_by_count":0,"area":"deeprl"},{"id":"2606.21350","title":"A Reward-Petri-Net Interpretation of Temporal Behavior Trees","created":"2026-06-19","cited_by_count":0,"area":"deeprl"},{"id":"2606.22922","title":"Hierarchical Reinforcement Learning for Sparse-Reward Search in Commutative Algebra","created":"2026-06-22","cited_by_count":0,"area":"deeprl"},{"id":"2606.26333","title":"Mesh-RL: Coupled subgrid reinforcement learning","created":"2026-06-24","cited_by_count":0,"area":"deeprl"},{"id":"2607.08925","title":"SafeExplorer: An Unbiased Policy Gradient for Reinforcement Learning with Recovery Interventions","created":"2026-07-09","cited_by_count":0,"area":"deeprl"},{"id":"2607.18368","title":"Neuro-Symbolic Meta-Policies for Temporal Knowledge-Graph Memory under Partial Observability","created":"2026-07-20","cited_by_count":0,"area":"deeprl"},{"id":"2607.23726","title":"Hierarchical Soft Actor-Critic for Sparse-Reward Long-Horizon Reinforcement Learning","created":"2026-07-26","cited_by_count":0,"area":"deeprl"},{"id":"2608.17030","title":"Lambda-Hold Control: Human-Like Movement Emerges from a Minimal Task Reward in Predictive Musculoskeletal Simulation","created":"2026-08-17","cited_by_count":0,"area":"deeprl"},{"id":"2609.39911","title":"Patient-Centered Treatment Planning for Chronic Multimorbidity: A Hierarchical Reinforcement Learning Framework for Preference Modeling","created":"2026-09-30","cited_by_count":0,"area":"deeprl"},{"id":"2610.03604","title":"Mastering Atari 2600 Games with Discovered Options","created":"2026-10-02","cited_by_count":0,"area":"deeprl"},{"id":"2610.05446","title":"Hierarchical Time-aware Bootstrapping for Off-Policy Subgoal Value Learning","created":"2026-10-04","cited_by_count":0,"area":"deeprl"},{"id":"2610.06019","title":"Adaptive Expert Guidance for Efficient On-Policy Reinforcement Learning","created":"2026-10-05","cited_by_count":0,"area":"deeprl"},{"id":"2610.12135","title":"Q-Shaped Options for Hierarchical Reinforcement Learning","created":"2026-10-08","cited_by_count":0,"area":"deeprl"},{"id":"2610.18188","title":"OneDemo: Unified Policy Learning and Data Generation from a Single Demonstration","created":"2026-10-13","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}