{"total":113,"rows":[{"id":"2408.15270","title":"SkillMimic: Learning Basketball Interaction Skills from Demonstrations","created":"2024-08-12","cited_by_count":30,"area":"deeprl"},{"id":"2406.06986","title":"DNN Partitioning, Task Offloading, and Resource Allocation in Dynamic Vehicular Networks: A Lyapunov-Guided Diffusion-Based Reinforcement Learning Approach","created":"2024-06-11","cited_by_count":17,"area":"deeprl"},{"id":"2407.00304","title":"A Review of Safe Reinforcement Learning Methods for Modern Power Systems","created":"2024-06-29","cited_by_count":11,"area":"deeprl"},{"id":"2501.15893","title":"Benchmarking Quantum Reinforcement Learning","created":"2025-01-27","cited_by_count":10,"area":"deeprl"},{"id":"2404.14238","title":"Beyond the Edge: An Advanced Exploration of Reinforcement Learning for Mobile Edge Computing, its Applications, and Future Research Trajectories","created":"2024-04-22","cited_by_count":9,"area":"deeprl"},{"id":"2411.05614","title":"Acceleration for Deep Reinforcement Learning using Parallel and Distributed Computing: A Survey","created":"2024-11-08","cited_by_count":8,"area":"deeprl"},{"id":"2403.15267","title":"Parametric PDE Control with Deep Reinforcement Learning and Differentiable L0-Sparse Polynomial Policies","created":"2024-03-22","cited_by_count":7,"area":"deeprl"},{"id":"2404.17070","title":"Deep Reinforcement Learning for Bipedal Locomotion: A Brief Survey","created":"2024-04-25","cited_by_count":7,"area":"deeprl"},{"id":"2405.16266","title":"Deep Reinforcement Learning with Enhanced PPO for Safe Mobile Robot Navigation","created":"2024-05-25","cited_by_count":7,"area":"deeprl"},{"id":"2405.19047","title":"Statistical Context Detection for Deep Lifelong Reinforcement Learning","created":"2024-05-29","cited_by_count":7,"area":"deeprl"},{"id":"2407.04522","title":"Graph Reinforcement Learning for Power Grids: A Comprehensive Survey","created":"2024-07-05","cited_by_count":7,"area":"deeprl"},{"id":"2410.20487","title":"Efficient Diversity-based Experience Replay for Deep Reinforcement Learning","created":"2024-10-27","cited_by_count":7,"area":"deeprl"},{"id":"2501.08669","title":"SPEQ: Offline Stabilization Phases for Efficient Q-Learning in High Update-To-Data Ratio Reinforcement Learning","created":"2025-01-15","cited_by_count":7,"area":"deeprl"},{"id":"2405.12308","title":"Continual Deep Reinforcement Learning for Decentralized Satellite Routing","created":"2024-05-20","cited_by_count":6,"area":"deeprl"},{"id":"2407.04803","title":"The Impact of Quantization and Pruning on Deep Reinforcement Learning Models","created":"2024-07-05","cited_by_count":6,"area":"deeprl"},{"id":"2410.11463","title":"Advanced Persistent Threats (APT) Attribution Using Deep Reinforcement Learning","created":"2024-10-15","cited_by_count":6,"area":"deeprl"},{"id":"2502.15794","title":"Self-Supervised Transformers as Iterative Solution Improvers for Constraint Satisfaction","created":"2025-02-18","cited_by_count":6,"area":"deeprl"},{"id":"2604.04539","title":"FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control","created":"2026-04-06","cited_by_count":5,"area":"deeprl"},{"id":"2401.13447","title":"Symbolic Equation Solving via Reinforcement Learning","created":"2024-01-24","cited_by_count":4,"area":"deeprl"},{"id":"2406.00887","title":"Deep Reinforcement Learning for Sim-to-Real Policy Transfer of VTOL-UAVs Offshore Docking Operations","created":"2024-06-02","cited_by_count":4,"area":"deeprl"},{"id":"2502.09417","title":"A Survey of Reinforcement Learning for Optimization in Automation","created":"2025-02-13","cited_by_count":4,"area":"deeprl"},{"id":"2505.02634","title":"Transfer learning-enhanced deep reinforcement learning for aerodynamic airfoil optimisation subject to structural constraints","created":"2025-05-05","cited_by_count":4,"area":"deeprl"},{"id":"2506.04627","title":"Enhancing Efficiency and Propulsion in Bio-mimetic Robotic Fish through End-to-End Deep Reinforcement Learning","created":"2025-06-05","cited_by_count":4,"area":"deeprl"},{"id":"2508.09128","title":"A Review On Safe Reinforcement Learning Using Lyapunov and Barrier Functions","created":"2025-08-12","cited_by_count":4,"area":"deeprl"},{"id":"2404.06330","title":"Generative Pre-Trained Transformer for Symbolic Regression Base In-Context Reinforcement Learning","created":"2024-04-09","cited_by_count":3,"area":"deeprl"},{"id":"2407.14486","title":"Explainable Post hoc Portfolio Management Financial Policy of a Deep Reinforcement Learning agent","created":"2024-07-19","cited_by_count":3,"area":"deeprl"},{"id":"2408.14518","title":"A Survey on Reinforcement Learning Applications in SLAM","created":"2024-08-26","cited_by_count":3,"area":"deeprl"},{"id":"2410.21109","title":"Dual-Agent Deep Reinforcement Learning for Dynamic Pricing and Replenishment","created":"2024-10-28","cited_by_count":3,"area":"deeprl"},{"id":"2501.04538","title":"HypeRL: Hypernetwork-Based Reinforcement Learning for Control of Parametrized Dynamical Systems","created":"2025-01-08","cited_by_count":3,"area":"deeprl"},{"id":"2501.04879","title":"Multilinear Tensor Low-Rank Approximation for Policy-Gradient Methods in Reinforcement Learning","created":"2025-01-08","cited_by_count":3,"area":"deeprl"},{"id":"2504.00626","title":"Probabilistically safe and efficient model-based reinforcement learning","created":"2025-04-01","cited_by_count":3,"area":"deeprl"},{"id":"2402.09290","title":"Learning Interpretable Policies in Hindsight-Observable POMDPs through Partially Supervised Reinforcement Learning","created":"2024-02-14","cited_by_count":2,"area":"deeprl"},{"id":"2402.11604","title":"Self-evolving Autoencoder Embedded Q-Network","created":"2024-02-18","cited_by_count":2,"area":"deeprl"},{"id":"2403.05693","title":"Shielded Deep Reinforcement Learning for Complex Spacecraft Tasking","created":"2024-03-08","cited_by_count":2,"area":"deeprl"},{"id":"2403.15100","title":"Subequivariant Reinforcement Learning Framework for Coordinated Motion Control","created":"2024-03-22","cited_by_count":2,"area":"deeprl"},{"id":"2404.03710","title":"Self-organized free-flight arrival for urban air mobility","created":"2024-04-04","cited_by_count":2,"area":"deeprl"},{"id":"2405.17625","title":"Matrix Low-Rank Trust Region Policy Optimization","created":"2024-05-27","cited_by_count":2,"area":"deeprl"},{"id":"2405.17626","title":"Matrix Low-Rank Approximation For Policy Gradient Methods","created":"2024-05-27","cited_by_count":2,"area":"deeprl"},{"id":"2407.02503","title":"Optimizing Deep Reinforcement Learning for Adaptive Robotic Arm Control","created":"2024-06-12","cited_by_count":2,"area":"deeprl"},{"id":"2407.08964","title":"Communication-Aware Reinforcement Learning for Cooperative Adaptive Cruise Control","created":"2024-07-12","cited_by_count":2,"area":"deeprl"},{"id":"2407.20651","title":"Towards Generalizable Reinforcement Learning via Causality-Guided Self-Adaptive Representations","created":"2024-07-30","cited_by_count":2,"area":"deeprl"},{"id":"2409.10048","title":"Audio-Driven Reinforcement Learning for Head-Orientation in Naturalistic Environments","created":"2024-09-16","cited_by_count":2,"area":"deeprl"},{"id":"2410.10737","title":"Asymptotic Analysis of Sample-averaged Q-learning","created":"2024-10-14","cited_by_count":2,"area":"deeprl"},{"id":"2502.10303","title":"Reinforcement Learning in Strategy-Based and Atari Games: A Review of Google DeepMinds Innovations","created":"2025-02-14","cited_by_count":2,"area":"deeprl"},{"id":"2503.03208","title":"Embodied Escaping: End-to-End Reinforcement Learning for Robot Navigation in Narrow Environment","created":"2025-03-05","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":"2504.20660","title":"Quantum-Enhanced Hybrid Reinforcement Learning Framework for Dynamic Path Planning in Autonomous Systems","created":"2025-04-29","cited_by_count":2,"area":"deeprl"},{"id":"2601.18626","title":"Rank-1 Approximation of Inverse Fisher for Natural Policy Gradients in Deep Reinforcement Learning","created":"2026-01-26","cited_by_count":2,"area":"deeprl"},{"id":"2402.00677","title":"Neural Policy Style Transfer","created":"2024-02-01","cited_by_count":1,"area":"deeprl"},{"id":"2402.11515","title":"Optimal Parallelization Strategies for Active Flow Control in Deep Reinforcement Learning-Based Computational Fluid Dynamics","created":"2024-02-18","cited_by_count":1,"area":"deeprl"},{"id":"2402.13654","title":"Improving a Proportional Integral Controller with Reinforcement Learning on a Throttle Valve Benchmark","created":"2024-02-21","cited_by_count":1,"area":"deeprl"},{"id":"2402.15617","title":"Reinforcement Learning-Based Approaches for Enhancing Security and Resilience in Smart Control: A Survey on Attack and Defense Methods","created":"2024-02-23","cited_by_count":1,"area":"deeprl"},{"id":"2402.17050","title":"Reinforcement Learning Based Oscillation Dampening: Scaling up Single-Agent RL algorithms to a 100 AV highway field operational test","created":"2024-02-26","cited_by_count":1,"area":"deeprl"},{"id":"2404.08423","title":"SIR-RL: Reinforcement Learning for Optimized Policy Control during Epidemiological Outbreaks in Emerging Market and Developing Economies","created":"2024-04-12","cited_by_count":1,"area":"deeprl"},{"id":"2407.12894","title":"Maintenance Strategies for Sewer Pipes with Multi-State Degradation and Deep Reinforcement Learning","created":"2024-07-17","cited_by_count":1,"area":"deeprl"},{"id":"2408.07712","title":"Introduction to Reinforcement Learning","created":"2024-08-13","cited_by_count":1,"area":"deeprl"},{"id":"2409.05435","title":"Semifactual Explanations for Reinforcement Learning","created":"2024-09-09","cited_by_count":1,"area":"deeprl"},{"id":"2410.04322","title":"Toward Debugging Deep Reinforcement Learning Programs with RLExplorer","created":"2024-10-06","cited_by_count":1,"area":"deeprl"},{"id":"2410.06828","title":"Transfer Learning for a Class of Cascade Dynamical Systems","created":"2024-10-09","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":"2503.16371","title":"Reinforcement Learning-based Heuristics to Guide Domain-Independent Dynamic Programming","created":"2025-03-20","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":"2506.16590","title":"Energy-Based Transfer for Reinforcement Learning","created":"2025-06-19","cited_by_count":1,"area":"deeprl"},{"id":"2511.02286","title":"Reinforcement learning based data assimilation for unknown state model","created":"2025-11-04","cited_by_count":1,"area":"deeprl"},{"id":"2511.06229","title":"Deep Reinforcement Learning for Dynamic Origin-Destination Matrix Estimation in Microscopic Traffic Simulations Considering Credit Assignment","created":"2025-11-09","cited_by_count":1,"area":"deeprl"},{"id":"2601.12577","title":"Primate-like perceptual decision making emerges through deep recurrent reinforcement learning","created":"2026-01-18","cited_by_count":1,"area":"deeprl"},{"id":"2402.06297","title":"Dynamic Q-planning for Online UAV Path Planning in Unknown and Complex Environments","created":"2024-02-09","cited_by_count":0,"area":"deeprl"},{"id":"2403.03643","title":"A Survey on Applications of Reinforcement Learning in Spatial Resource Allocation","created":"2024-03-06","cited_by_count":0,"area":"deeprl"},{"id":"2403.04329","title":"A mechanism-driven reinforcement learning framework for shape optimization of airfoils","created":"2024-03-07","cited_by_count":0,"area":"deeprl"},{"id":"2403.07566","title":"An Improved Strategy for Blood Glucose Control Using Multi-Step Deep Reinforcement Learning","created":"2024-03-12","cited_by_count":0,"area":"deeprl"},{"id":"2403.10761","title":"Scheduling Drone and Mobile Charger via Hybrid-Action Deep Reinforcement Learning","created":"2024-03-16","cited_by_count":0,"area":"deeprl"},{"id":"2404.11834","title":"Actor-Critic Reinforcement Learning with Phased Actor","created":"2024-04-18","cited_by_count":0,"area":"deeprl"},{"id":"2406.04575","title":"Optimization of geological carbon storage operations with multimodal latent dynamic model and deep reinforcement learning","created":"2024-06-07","cited_by_count":0,"area":"deeprl"},{"id":"2406.13568","title":"Trapezoidal Gradient Descent for Effective Reinforcement Learning in Spiking Networks","created":"2024-06-19","cited_by_count":0,"area":"deeprl"},{"id":"2406.14697","title":"A Benchmark Study of Deep-RL Methods for Maximum Coverage Problems over Graphs","created":"2024-06-20","cited_by_count":0,"area":"deeprl"},{"id":"2407.00744","title":"Disentangled Representations for Causal Cognition","created":"2024-06-30","cited_by_count":0,"area":"deeprl"},{"id":"2407.09877","title":"Model-free Distortion Canceling and Control of Quantum Devices","created":"2024-07-13","cited_by_count":0,"area":"deeprl"},{"id":"2407.20466","title":"A Method for Fast Autonomy Transfer in Reinforcement Learning","created":"2024-07-29","cited_by_count":0,"area":"deeprl"},{"id":"2408.04376","title":"Deep Reinforcement Learning for the Design of Metamaterial Mechanisms with Functional Compliance Control","created":"2024-08-08","cited_by_count":0,"area":"deeprl"},{"id":"2408.13018","title":"Robust Iterative Value Conversion: Deep Reinforcement Learning for Neurochip-driven Edge Robots","created":"2024-08-23","cited_by_count":0,"area":"deeprl"},{"id":"2409.18597","title":"TemporalPaD: a reinforcement-learning framework for temporal feature representation and dimension reduction","created":"2024-09-27","cited_by_count":0,"area":"deeprl"},{"id":"2410.11250","title":"Learning Agents With Prioritization and Parameter Noise in Continuous State and Action Space","created":"2024-10-15","cited_by_count":0,"area":"deeprl"},{"id":"2410.21240","title":"Quantum Reinforcement Learning-Based Two-Stage Unit Commitment Framework for Enhanced Power Systems Robustness","created":"2024-10-28","cited_by_count":0,"area":"deeprl"},{"id":"2411.02559","title":"Dynamic Weight Adjusting Deep Q-Networks for Real-Time Environmental Adaptation","created":"2024-11-04","cited_by_count":0,"area":"deeprl"},{"id":"2412.07402","title":"Non-Progressive Influence Maximization in Dynamic Social Networks","created":"2024-12-10","cited_by_count":0,"area":"deeprl"},{"id":"2412.17908","title":"Trading Devil RL: Backdoor attack via Stock market, Bayesian Optimization and Reinforcement Learning","created":"2024-12-23","cited_by_count":0,"area":"deeprl"},{"id":"2502.17307","title":"Survey on Strategic Mining in Blockchain: A Reinforcement Learning Approach","created":"2025-02-24","cited_by_count":0,"area":"deeprl"},{"id":"2503.09391","title":"Context-aware Constrained Reinforcement Learning Based Energy-Efficient Power Scheduling for Non-stationary XR Data Traffic","created":"2025-03-12","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":"2504.09929","title":"Moderate Actor-Critic Methods: Controlling Overestimation Bias via Expectile Loss","created":"2025-04-14","cited_by_count":0,"area":"deeprl"},{"id":"2504.17006","title":"A Systematic Approach to Design Real-World Human-in-the-Loop Deep Reinforcement Learning: Salient Features, Challenges and Trade-offs","created":"2025-04-23","cited_by_count":0,"area":"deeprl"},{"id":"2504.19142","title":"BQSched: A Non-intrusive Scheduler for Batch Concurrent Queries via Reinforcement Learning","created":"2025-04-27","cited_by_count":0,"area":"deeprl"},{"id":"2505.07043","title":"Design and Experimental Test of Datatic Approximate Optimal Filter in Nonlinear Dynamic Systems","created":"2025-05-11","cited_by_count":0,"area":"deeprl"},{"id":"2506.13478","title":"Learning Swing-up Maneuvers for a Suspended Aerial Manipulation Platform in a Hierarchical Control Framework","created":"2025-06-16","cited_by_count":0,"area":"deeprl"},{"id":"2507.08366","title":"Intelligent Control of Spacecraft Reaction Wheel Attitude Using Deep Reinforcement Learning","created":"2025-07-11","cited_by_count":0,"area":"deeprl"},{"id":"2507.10030","title":"Finetuning Deep Reinforcement Learning Policies with Evolutionary Strategies for Control of Underactuated Robots","created":"2025-07-14","cited_by_count":0,"area":"deeprl"},{"id":"2507.10990","title":"Adaptive Policy Synchronization for Scalable Reinforcement Learning","created":"2025-07-15","cited_by_count":0,"area":"deeprl"},{"id":"2507.14487","title":"Federated Reinforcement Learning in Heterogeneous Environments","created":"2025-07-19","cited_by_count":0,"area":"deeprl"},{"id":"2508.15588","title":"A Dynamical Systems Framework for Reinforcement Learning Safety and Robustness Verification","created":"2025-08-21","cited_by_count":0,"area":"deeprl"},{"id":"2509.11016","title":"Deep Reinforcement Learning-Assisted Component Auto-Configuration of Differential Evolution Algorithm for Constrained Optimization: A Foundation Model","created":"2025-09-14","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}