{"total":57,"rows":[{"id":"2401.09561","title":"Sharing Knowledge in Multi-Task Deep Reinforcement Learning","created":"2024-01-17","cited_by_count":44,"area":"deeprl"},{"id":"2408.10932","title":"The Evolution of Reinforcement Learning in Quantitative Finance: A Survey","created":"2024-08-20","cited_by_count":11,"area":"deeprl"},{"id":"2506.14811","title":"Self-Composing Policies for Scalable Continual Reinforcement Learning","created":"2025-06-04","cited_by_count":11,"area":"deeprl"},{"id":"2403.12193","title":"Continual Domain Randomization","created":"2024-03-18","cited_by_count":8,"area":"deeprl"},{"id":"2410.16411","title":"The Duality of Generative AI and Reinforcement Learning in Robotics: A Review","created":"2024-10-21","cited_by_count":6,"area":"deeprl"},{"id":"2505.20619","title":"Gait-Conditioned Reinforcement Learning with Multi-Phase Curriculum for Humanoid Locomotion","created":"2025-05-27","cited_by_count":6,"area":"deeprl"},{"id":"2403.11907","title":"Distill2Explain: Differentiable decision trees for explainable reinforcement learning in energy application controllers","created":"2024-03-18","cited_by_count":5,"area":"deeprl"},{"id":"2410.14371","title":"Interpretable end-to-end Neurosymbolic Reinforcement Learning agents","created":"2024-10-18","cited_by_count":4,"area":"deeprl"},{"id":"2404.05950","title":"Efficient Multi-Task Reinforcement Learning via Task-Specific Action Correction","created":"2024-04-09","cited_by_count":2,"area":"deeprl"},{"id":"2412.04847","title":"Enabling Energy-Efficient Simultaneous Multi-Task Reinforcement Learning through Spiking Neural Networks with Active Dendrites for Bio-inspired Generalist Agents","created":"2024-12-06","cited_by_count":2,"area":"deeprl"},{"id":"2502.05069","title":"Exploring the Generalizability of Geomagnetic Navigation: A Deep Reinforcement Learning approach with Policy Distillation","created":"2025-02-07","cited_by_count":2,"area":"deeprl"},{"id":"2505.18447","title":"Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement Learning","created":"2025-05-24","cited_by_count":2,"area":"deeprl"},{"id":"2506.06410","title":"Delphos: A reinforcement learning framework for assisting discrete choice model specification","created":"2025-06-06","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":"2511.11607","title":"Clustering-Based Weight Orthogonalization for Stabilizing Deep Reinforcement Learning","created":"2025-11-02","cited_by_count":2,"area":"deeprl"},{"id":"2404.19462","title":"Continual Model-based Reinforcement Learning for Data Efficient Wireless Network Optimisation","created":"2024-04-30","cited_by_count":1,"area":"deeprl"},{"id":"2406.01838","title":"Learning the Target Network in Function Space","created":"2024-06-03","cited_by_count":1,"area":"deeprl"},{"id":"2408.10858","title":"Centralized Reward Agent for Knowledge Sharing and Transfer in Multi-Task Reinforcement Learning","created":"2024-08-20","cited_by_count":1,"area":"deeprl"},{"id":"2501.14443","title":"Learning more with the same effort: how randomization improves the robustness of a robotic deep reinforcement learning agent","created":"2025-01-24","cited_by_count":1,"area":"deeprl"},{"id":"2503.00345","title":"Towards Understanding the Benefit of Multitask Representation Learning in Decision Process","created":"2025-03-01","cited_by_count":1,"area":"deeprl"},{"id":"2503.02030","title":"Accelerating Multi-Task Temporal Difference Learning under Low-Rank Representation","created":"2025-03-03","cited_by_count":1,"area":"deeprl"},{"id":"2505.16581","title":"How Ensembles of Distilled Policies Improve Generalisation in Reinforcement Learning","created":"2025-05-22","cited_by_count":1,"area":"deeprl"},{"id":"2506.03225","title":"Multiple-Frequencies Population-Based Training","created":"2025-06-03","cited_by_count":1,"area":"deeprl"},{"id":"2506.07006","title":"CARoL: Context-aware Adaptation for Robot Learning","created":"2025-06-08","cited_by_count":1,"area":"deeprl"},{"id":"2506.12735","title":"Revealing the Challenges of Sim-to-Real Transfer in Model-Based Reinforcement Learning via Latent Space Modeling","created":"2025-06-15","cited_by_count":1,"area":"deeprl"},{"id":"2506.16590","title":"Energy-Based Transfer for Reinforcement Learning","created":"2025-06-19","cited_by_count":1,"area":"deeprl"},{"id":"2507.07848","title":"\"So, Tell Me About Your Policy...\": Distillation of interpretable policies from Deep Reinforcement Learning agents","created":"2025-07-10","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":"2404.17892","title":"Shared learning of powertrain control policies for vehicle fleets","created":"2024-04-27","cited_by_count":0,"area":"deeprl"},{"id":"2405.02456","title":"Natural Policy Gradient and Actor Critic Methods for Constrained Multi-Task Reinforcement Learning","created":"2024-05-03","cited_by_count":0,"area":"deeprl"},{"id":"2411.10367","title":"Continual Adversarial Reinforcement Learning (CARL) of False Data Injection detection: forgetting and explainability","created":"2024-11-15","cited_by_count":0,"area":"deeprl"},{"id":"2505.12350","title":"Multi-CALF: A Policy Combination Approach with Statistical Guarantees","created":"2025-05-18","cited_by_count":0,"area":"deeprl"},{"id":"2507.17275","title":"Prolonging Tool Life: Learning Skillful Use of General-purpose Tools through Lifespan-guided Reinforcement Learning","created":"2025-07-23","cited_by_count":0,"area":"deeprl"},{"id":"2508.09277","title":"Value Function Initialization for Knowledge Transfer and Jump-start in Deep Reinforcement Learning","created":"2025-08-12","cited_by_count":0,"area":"deeprl"},{"id":"2509.19892","title":"D3Grasp: Diverse and Deformable Dexterous Grasping for General Objects","created":"2025-09-24","cited_by_count":0,"area":"deeprl"},{"id":"2509.20766","title":"Leveraging Temporally Extended Behavior Sharing for Multi-task Reinforcement Learning","created":"2025-09-25","cited_by_count":0,"area":"deeprl"},{"id":"2511.22104","title":"Representative Action Selection for Large Action Space: From Bandits to MDPs","created":"2025-11-27","cited_by_count":0,"area":"deeprl"},{"id":"2512.22910","title":"Sat-EnQ: Satisficing Ensembles of Weak Q-Learners for Reliable and Compute-Efficient Reinforcement Learning","created":"2025-12-28","cited_by_count":0,"area":"deeprl"},{"id":"2601.16677","title":"Sim-to-Real Transfer via a Style-Identified Cycle Consistent Generative Adversarial Network: Zero-Shot Deployment on Robotic Manipulators through Visual Domain Adaptation","created":"2026-01-23","cited_by_count":0,"area":"deeprl"},{"id":"2602.14578","title":"RNM-TD3: N:M Semi-structured Sparse Reinforcement Learning From Scratch","created":"2026-02-16","cited_by_count":0,"area":"deeprl"},{"id":"2603.00903","title":"Principled Fast and Meta Knowledge Learners for Continual Reinforcement Learning","created":"2026-03-01","cited_by_count":0,"area":"deeprl"},{"id":"2604.02353","title":"Prism: Policy Reuse via Interpretable Strategy Mapping in Reinforcement Learning","created":"2026-03-04","cited_by_count":0,"area":"deeprl"},{"id":"2604.09452","title":"SafeAdapt: Provably Safe Policy Updates in Deep Reinforcement Learning","created":"2026-04-10","cited_by_count":0,"area":"deeprl"},{"id":"2604.27411","title":"Detecting is Easy, Adapting is Hard: Local Expert Growth for Visual Model-Based Reinforcement Learning under Distribution Shift","created":"2026-04-30","cited_by_count":0,"area":"deeprl"},{"id":"2605.02159","title":"Combining Trained Models in Reinforcement Learning","created":"2026-05-04","cited_by_count":0,"area":"deeprl"},{"id":"2605.10648","title":"Demystifying Deep Reinforcement Learning: A Neuro-Symbolic Framework for Interpretable Open RAN Automation","created":"2026-05-11","cited_by_count":0,"area":"deeprl"},{"id":"2605.13665","title":"Robot Squid Game: Quadrupedal Locomotion for Traversing Narrow Tunnels","created":"2026-05-13","cited_by_count":0,"area":"deeprl"},{"id":"2605.14897","title":"Critic-Driven Voronoi-Quantization for Distilling Deep RL Policies to Explainable Models","created":"2026-05-14","cited_by_count":0,"area":"deeprl"},{"id":"2605.19924","title":"RoHIL: Robust Human-in-the-Loop Robotic Reinforcement Learning Against Illumination Variations","created":"2026-05-19","cited_by_count":0,"area":"deeprl"},{"id":"2606.02280","title":"Dynamics Are Learned, Not Told: Semi-Supervised Discovery of Latent Dynamics Geometries For Zero-Shot Policy Adaptation","created":"2026-06-01","cited_by_count":0,"area":"deeprl"},{"id":"2606.28152","title":"Regularized Reward-Punishment Reinforcement Learning","created":"2026-06-26","cited_by_count":0,"area":"deeprl"},{"id":"2608.17180","title":"Task Specialization Fine-Tuning for Contextual Reinforcement Learning","created":"2026-08-17","cited_by_count":0,"area":"deeprl"},{"id":"2608.30765","title":"T3S: Improving Multi-Task Reinforcement Learning with Task-Specific Feature Selector and Scheduler","created":"2026-08-31","cited_by_count":0,"area":"deeprl"},{"id":"2609.23483","title":"STRIDER: Stepping-Enabled Multi-Gait Hierarchical 3D Loco-Manipulation Framework for Humanoid Robots","created":"2026-09-20","cited_by_count":0,"area":"deeprl"},{"id":"2609.38852","title":"Locomotion-Grounded Humanoid Soccer: Task-Gated Reinforcement Learning of a Multi-Directional Kicking Library","created":"2026-09-30","cited_by_count":0,"area":"deeprl"},{"id":"2610.03475","title":"Single or Multiple Policies for Phase-Structured Reinforcement Learning?","created":"2026-10-02","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"}],"next_cursor":null}