{"total":90,"rows":[{"id":"2401.08898","title":"Bridging State and History Representations: Understanding Self-Predictive RL","created":"2024-01-17","cited_by_count":54,"area":"deeprl"},{"id":"2502.10550","title":"Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning","created":"2025-02-14","cited_by_count":36,"area":"deeprl"},{"id":"2408.14336","title":"Equivariant Reinforcement Learning under Partial Observability","created":"2024-08-26","cited_by_count":18,"area":"deeprl"},{"id":"2506.21872","title":"A Survey of Continual Reinforcement Learning","created":"2025-06-27","cited_by_count":18,"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":"2409.01449","title":"Real-Time Recurrent Learning using Trace Units in Reinforcement Learning","created":"2024-09-02","cited_by_count":10,"area":"deeprl"},{"id":"2503.15200","title":"Partially Observable Reinforcement Learning with Memory Traces","created":"2025-03-19","cited_by_count":9,"area":"deeprl"},{"id":"2410.21795","title":"Robot Policy Learning with Temporal Optimal Transport Reward","created":"2024-10-29","cited_by_count":8,"area":"deeprl"},{"id":"2407.07333","title":"Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy","created":"2024-07-10","cited_by_count":7,"area":"deeprl"},{"id":"2508.00046","title":"Benchmarking Partial Observability in Reinforcement Learning with a Suite of Memory-Improvable Domains","created":"2025-07-31","cited_by_count":7,"area":"deeprl"},{"id":"2510.21110","title":"Confounding Robust Deep Reinforcement Learning: A Causal Approach","created":"2025-10-24","cited_by_count":7,"area":"deeprl"},{"id":"2402.09900","title":"Recurrent Reinforcement Learning with Memoroids","created":"2024-02-15","cited_by_count":6,"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":"2501.19116","title":"A Theoretical Justification for Asymmetric Actor-Critic Algorithms","created":"2025-01-31","cited_by_count":6,"area":"deeprl"},{"id":"2506.15446","title":"Zero-Shot Reinforcement Learning Under Partial Observability","created":"2025-06-18","cited_by_count":6,"area":"deeprl"},{"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":"2409.16824","title":"Uncertainty Representations in State-Space Layers for Deep Reinforcement Learning under Partial Observability","created":"2024-09-25","cited_by_count":5,"area":"deeprl"},{"id":"2412.06531","title":"Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation","created":"2024-12-09","cited_by_count":5,"area":"deeprl"},{"id":"2503.14555","title":"A Generalist Hanabi Agent","created":"2025-03-17","cited_by_count":5,"area":"deeprl"},{"id":"2402.07102","title":"An Empirical Study on the Power of Future Prediction in Partially Observable Environments","created":"2024-02-11","cited_by_count":4,"area":"deeprl"},{"id":"2602.08690","title":"SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity","created":"2026-02-09","cited_by_count":4,"area":"deeprl"},{"id":"2407.20917","title":"How to Choose a Reinforcement-Learning Algorithm","created":"2024-07-30","cited_by_count":3,"area":"deeprl"},{"id":"2411.03604","title":"Temporal-Difference Learning Using Distributed Error Signals","created":"2024-11-06","cited_by_count":3,"area":"deeprl"},{"id":"2503.01450","title":"Investigating Memory in Model-Free RL with POPGym Arcade","created":"2025-03-03","cited_by_count":3,"area":"deeprl"},{"id":"2506.18482","title":"Reliability-Adjusted Prioritized Experience Replay","created":"2025-06-23","cited_by_count":3,"area":"deeprl"},{"id":"2508.21101","title":"Beyond Prediction: Reinforcement Learning as the Defining Leap in Healthcare AI","created":"2025-08-28","cited_by_count":3,"area":"deeprl"},{"id":"2404.14552","title":"Generalizing Multi-Step Inverse Models for Representation Learning to Finite-Memory POMDPs","created":"2024-04-22","cited_by_count":2,"area":"deeprl"},{"id":"2407.18597","title":"Reinforcement Learning for Sustainable Energy: A Survey","created":"2024-07-26","cited_by_count":2,"area":"deeprl"},{"id":"2503.13200","title":"Timing the Match: A Deep Reinforcement Learning Approach for Ride-Hailing and Ride-Pooling Services","created":"2025-03-17","cited_by_count":2,"area":"deeprl"},{"id":"2509.12085","title":"Compositional shield synthesis for safe reinforcement learning in partial observability","created":"2025-09-15","cited_by_count":2,"area":"deeprl"},{"id":"2509.20008","title":"Learning Robust Penetration Testing Policies under Partial Observability: A systematic evaluation","created":"2025-09-24","cited_by_count":2,"area":"deeprl"},{"id":"2509.26000","title":"Informed Asymmetric Actor-Critic: Leveraging Privileged Signals Beyond Full-State Access","created":"2025-09-30","cited_by_count":2,"area":"deeprl"},{"id":"2512.18892","title":"Structural Reinforcement Learning for Heterogeneous Agent Macroeconomics","created":"2025-12-21","cited_by_count":2,"area":"deeprl"},{"id":"2606.06746","title":"Performance Variation in Deep Reinforcement Learning","created":"2026-06-04","cited_by_count":2,"area":"deeprl"},{"id":"2405.09086","title":"Chaos-based reinforcement learning with TD3","created":"2024-05-15","cited_by_count":1,"area":"deeprl"},{"id":"2406.06184","title":"Deep Multi-Objective Reinforcement Learning for Utility-Based Infrastructural Maintenance Optimization","created":"2024-06-10","cited_by_count":1,"area":"deeprl"},{"id":"2412.02334","title":"Reinforcement learning to learn quantum states for Heisenberg scaling accuracy","created":"2024-12-03","cited_by_count":1,"area":"deeprl"},{"id":"2501.04068","title":"Explainable Reinforcement Learning for Formula One Race Strategy","created":"2025-01-07","cited_by_count":1,"area":"deeprl"},{"id":"2504.18253","title":"Depth-Constrained ASV Navigation with Deep RL and Limited Sensing","created":"2025-04-25","cited_by_count":1,"area":"deeprl"},{"id":"2510.02149","title":"Reinforcement Learning with Action-Triggered Observations","created":"2025-10-02","cited_by_count":1,"area":"deeprl"},{"id":"2602.00399","title":"Reinforcement Learning for Control Systems with Time Delays: A Comprehensive Survey","created":"2026-01-30","cited_by_count":1,"area":"deeprl"},{"id":"2602.08734","title":"Finite-State Controllers for (Hidden-Model) POMDPs using Deep Reinforcement Learning","created":"2026-02-09","cited_by_count":1,"area":"deeprl"},{"id":"2602.23242","title":"A Model-Free Universal AI","created":"2026-02-26","cited_by_count":1,"area":"deeprl"},{"id":"2603.04648","title":"When Sensors Fail: Temporal Sequence Models for Robust PPO under Sensor Drift","created":"2026-03-04","cited_by_count":1,"area":"deeprl"},{"id":"2605.16318","title":"Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning","created":"2026-05-04","cited_by_count":1,"area":"deeprl"},{"id":"2606.06227","title":"Reward hacking in physical reinforcement learning revealed by turbulent drag reduction","created":"2026-06-04","cited_by_count":1,"area":"deeprl"},{"id":"2606.20411","title":"Direct Advantage Estimation for Scalable and Sample-efficient Deep Reinforcement Learning","created":"2026-06-18","cited_by_count":1,"area":"deeprl"},{"id":"2404.01557","title":"Distributed Autonomous Swarm Formation for Dynamic Network Bridging","created":"2024-04-02","cited_by_count":0,"area":"deeprl"},{"id":"2410.12820","title":"A transformer-based deep reinforcement learning approach to spatial navigation in a partially observable Morris Water Maze","created":"2024-10-01","cited_by_count":0,"area":"deeprl"},{"id":"2502.19356","title":"Recurrent Auto-Encoders for Enhanced Deep Reinforcement Learning in Wilderness Search and Rescue Planning","created":"2025-02-26","cited_by_count":0,"area":"deeprl"},{"id":"2503.15895","title":"CONTHER: Context-Aware Reinforcement Learning for Robotic Manipulation with Sparse Rewards","created":"2025-03-20","cited_by_count":0,"area":"deeprl"},{"id":"2505.11153","title":"Bi-directional Recurrence Improves Transformer in Partially Observable Markov Decision Processes","created":"2025-05-16","cited_by_count":0,"area":"deeprl"},{"id":"2505.23857","title":"A Convolution and Attention Based Encoder for Reinforcement Learning under Partial Observability","created":"2025-05-29","cited_by_count":0,"area":"deeprl"},{"id":"2506.19353","title":"Partially Observable Residual Reinforcement Learning for PV-Inverter-Based Voltage Control in Distribution Grids","created":"2025-06-24","cited_by_count":0,"area":"deeprl"},{"id":"2508.01287","title":"Exploitation Is All You Need... for Exploration","created":"2025-08-02","cited_by_count":0,"area":"deeprl"},{"id":"2508.21314","title":"Convergence of regularized agent-state-based Q-learning in POMDPs","created":"2025-08-29","cited_by_count":0,"area":"deeprl"},{"id":"2509.00329","title":"Jacobian Exploratory Dual-Phase Reinforcement Learning for Dynamic Endoluminal Navigation of Deformable Continuum Robots","created":"2025-08-30","cited_by_count":0,"area":"deeprl"},{"id":"2510.06649","title":"Local Reinforcement Learning with Action-Conditioned Root Mean Squared Q-Functions","created":"2025-10-08","cited_by_count":0,"area":"deeprl"},{"id":"2510.13367","title":"A New Perspective on Transformers in Online Reinforcement Learning for Continuous Control","created":"2025-10-15","cited_by_count":0,"area":"deeprl"},{"id":"2512.06204","title":"Quantifying Memory Use in Reinforcement Learning with Temporal Range","created":"2025-12-05","cited_by_count":0,"area":"deeprl"},{"id":"2512.13890","title":"Group-Theoretic Reinforcement Learning of Dynamical Decoupling Sequences","created":"2025-12-15","cited_by_count":0,"area":"deeprl"},{"id":"2512.18604","title":"Trajectory Planning for UAV-Based Smart Farming Using Imitation-Based Triple Deep Q-Learning","created":"2025-12-21","cited_by_count":0,"area":"deeprl"},{"id":"2512.20513","title":"Recurrent Off-Policy Deep Reinforcement Learning Doesn't Have to be Slow","created":"2025-12-23","cited_by_count":0,"area":"deeprl"},{"id":"2512.21412","title":"A Survey of Freshness-Aware Wireless Networking with Reinforcement Learning","created":"2025-12-24","cited_by_count":0,"area":"deeprl"},{"id":"2601.04083","title":"Cells on Autopilot: Adaptive Cell (Re)Selection via Reinforcement Learning","created":"2026-01-07","cited_by_count":0,"area":"deeprl"},{"id":"2602.01196","title":"Unraveling the Hidden Dynamical Structure in Recurrent Neural Policies","created":"2026-02-01","cited_by_count":0,"area":"deeprl"},{"id":"2602.06088","title":"Transformer-Based Reinforcement Learning for Autonomous Orbital Collision Avoidance in Partially Observable Environments","created":"2026-02-05","cited_by_count":0,"area":"deeprl"},{"id":"2602.19428","title":"Sizing of Battery Considering Renewable Energy Bidding Strategy with Reinforcement Learning","created":"2026-02-23","cited_by_count":0,"area":"deeprl"},{"id":"2603.28790","title":"Learning to Remember: Attentive Reinforcement Learning for Edge Serverless Autoscaling","created":"2026-03-21","cited_by_count":0,"area":"deeprl"},{"id":"2604.04662","title":"Anticipatory Reinforcement Learning: From Generative Path-Laws to Distributional Value Functions","created":"2026-04-06","cited_by_count":0,"area":"deeprl"},{"id":"2604.07428","title":"Regret-Aware Policy Optimization: Environment-Level Memory for Replay Suppression under Delayed Harm","created":"2026-04-08","cited_by_count":0,"area":"deeprl"},{"id":"2604.09671","title":"Belief-State RWKV for Reinforcement Learning under Partial Observability","created":"2026-04-01","cited_by_count":0,"area":"deeprl"},{"id":"2604.15289","title":"Abstract Sim2Real through Approximate Information States","created":"2026-04-16","cited_by_count":0,"area":"deeprl"},{"id":"2605.01131","title":"Forager: a lightweight testbed for continual learning with partial observability in RL","created":"2026-05-01","cited_by_count":0,"area":"deeprl"},{"id":"2605.07057","title":"From Causal Graphs to Markovian States: Multi-Order State Exposure for Deep RL","created":"2026-05-08","cited_by_count":0,"area":"deeprl"},{"id":"2605.10377","title":"PC3D: Zero-Shot Cooperation Across Variable Rosters via Personalized Context Distillation","created":"2026-05-11","cited_by_count":0,"area":"deeprl"},{"id":"2605.10546","title":"Higher Resolution, Better Generalization: Unlocking Visual Scaling in Deep Reinforcement Learning","created":"2026-05-11","cited_by_count":0,"area":"deeprl"},{"id":"2605.12206","title":"Train Short, Act Long: Multistability and the Horizon Independence of Recurrent Policies","created":"2026-05-12","cited_by_count":0,"area":"deeprl"},{"id":"2605.18881","title":"Emergence of a Flow-Assisted Casting Strategy for Olfactory Navigation via Memory-Augmented Reinforcement Learning","created":"2026-05-16","cited_by_count":0,"area":"deeprl"},{"id":"2605.22142","title":"Short-Term-to-Long-Term Memory Transfer for Knowledge Graphs under Partial Observability","created":"2026-05-21","cited_by_count":0,"area":"deeprl"},{"id":"2605.26155","title":"When Does Adaptive Guidance Help? Belief-Aware Privileged Distillation for Autonomous Driving Under Partial Observability","created":"2026-05-24","cited_by_count":0,"area":"deeprl"},{"id":"2605.30612","title":"ZAPS-DA: Zero-Phase Action Policy Smoothing with Decoupled Actor for Continuous Control in Reinforcement Learning","created":"2026-05-28","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":"2608.05111","title":"Reward Structure Shapes the Interaction Between Episodic Exploration and Neural Memory in Reinforcement Learning","created":"2026-08-05","cited_by_count":0,"area":"deeprl"},{"id":"2608.15715","title":"Continuous Quantum Feedback Control via Kraus-Parameterized Belief Reinforcement Learning","created":"2026-08-16","cited_by_count":0,"area":"deeprl"},{"id":"2609.23374","title":"The Evidence Ladder for Reinforcement Learning in Healthcare: From Retrospective Policies to Trusted Interventions","created":"2026-09-20","cited_by_count":0,"area":"deeprl"},{"id":"2609.36867","title":"State Trace Rationale As Auxiliary Task in Reinforcement Learning","created":"2026-09-29","cited_by_count":0,"area":"deeprl"},{"id":"2609.38598","title":"Reinforcement Learning with Complex (valued) Memories","created":"2026-09-29","cited_by_count":0,"area":"deeprl"},{"id":"2610.03830","title":"Memory-State Critic for Asymmetric Actor-Critic with Application to Vision-Based Pursuit-Evasion","created":"2026-10-02","cited_by_count":0,"area":"deeprl"},{"id":"2610.13197","title":"Does Learning Recurrent Networks Matter in Partially Observable RL?","created":"2026-10-09","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}