{"total":76,"rows":[{"id":"2502.20396","title":"Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids","created":"2025-02-27","cited_by_count":48,"area":"deeprl"},{"id":"2502.02133","title":"Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classification","created":"2025-02-04","cited_by_count":26,"area":"deeprl"},{"id":"2407.03302","title":"A Review of the Applications of Deep Learning-Based Emergent Communication","created":"2024-07-03","cited_by_count":17,"area":"deeprl"},{"id":"2401.11555","title":"VQC-Based Reinforcement Learning with Data Re-uploading: Performance and Trainability","created":"2024-01-21","cited_by_count":12,"area":"deeprl"},{"id":"2407.08590","title":"A Review of Nine Physics Engines for Reinforcement Learning Research","created":"2024-07-11","cited_by_count":12,"area":"deeprl"},{"id":"2505.19850","title":"DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning","created":"2025-05-26","cited_by_count":12,"area":"deeprl"},{"id":"2401.12205","title":"Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization","created":"2024-01-22","cited_by_count":10,"area":"deeprl"},{"id":"2405.00629","title":"HUGO -- Highlighting Unseen Grid Options: Combining Deep Reinforcement Learning with a Heuristic Target Topology Approach","created":"2024-05-01","cited_by_count":10,"area":"deeprl"},{"id":"2510.04786","title":"Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning","created":"2025-10-06","cited_by_count":9,"area":"deeprl"},{"id":"2410.07574","title":"Gap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition","created":"2024-10-10","cited_by_count":8,"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":"2411.00401","title":"Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayes Theory","created":"2024-11-01","cited_by_count":7,"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":"2509.00338","title":"Scalable Option Learning in High-Throughput Environments","created":"2025-08-30","cited_by_count":5,"area":"deeprl"},{"id":"2409.04467","title":"State and Action Factorization in Power Grids","created":"2024-09-03","cited_by_count":3,"area":"deeprl"},{"id":"2505.15544","title":"A Temporal Difference Method for Stochastic Continuous Dynamics","created":"2025-05-21","cited_by_count":3,"area":"deeprl"},{"id":"2507.00257","title":"Gym4ReaL: A Suite for Benchmarking Real-World Reinforcement Learning","created":"2025-06-30","cited_by_count":3,"area":"deeprl"},{"id":"2406.05027","title":"Optimizing Automatic Differentiation with Deep Reinforcement Learning","created":"2024-06-07","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":"2411.11318","title":"Syllabus: Portable Curricula for Reinforcement Learning Agents","created":"2024-11-18","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":"2503.20688","title":"Graph-Enhanced Model-Free Reinforcement Learning Agents for Efficient Power Grid Topological Control","created":"2025-03-26","cited_by_count":2,"area":"deeprl"},{"id":"2504.12045","title":"pix2pockets: Shot Suggestions in 8-Ball Pool from a Single Image in the Wild","created":"2025-04-16","cited_by_count":2,"area":"deeprl"},{"id":"2506.04626","title":"Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learning","created":"2025-06-05","cited_by_count":2,"area":"deeprl"},{"id":"2510.02590","title":"Use the Online Network If You Can: Towards Fast and Stable Reinforcement Learning","created":"2025-10-02","cited_by_count":2,"area":"deeprl"},{"id":"2510.20314","title":"Enhancing Security in Deep Reinforcement Learning: A Comprehensive Survey on Adversarial Attacks and Defenses","created":"2025-10-23","cited_by_count":2,"area":"deeprl"},{"id":"2510.22158","title":"Solving Continuous Mean Field Games: Deep Reinforcement Learning for Non-Stationary Dynamics","created":"2025-10-25","cited_by_count":2,"area":"deeprl"},{"id":"2510.25951","title":"Estimating cognitive biases with attention-aware inverse planning","created":"2025-10-29","cited_by_count":2,"area":"deeprl"},{"id":"2605.16692","title":"EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous Control","created":"2026-05-15","cited_by_count":2,"area":"deeprl"},{"id":"2401.12822","title":"Deep Learning Based Simulators for the Phosphorus Removal Process Control in Wastewater Treatment via Deep Reinforcement Learning Algorithms","created":"2024-01-23","cited_by_count":1,"area":"deeprl"},{"id":"2402.03146","title":"A Multi-step Loss Function for Robust Learning of the Dynamics in Model-based Reinforcement Learning","created":"2024-02-05","cited_by_count":1,"area":"deeprl"},{"id":"2402.06075","title":"Scaling Artificial Intelligence for Digital Wargaming in Support of Decision-Making","created":"2024-02-08","cited_by_count":1,"area":"deeprl"},{"id":"2402.17375","title":"Impact of Computation in Integral Reinforcement Learning for Continuous-Time Control","created":"2024-02-27","cited_by_count":1,"area":"deeprl"},{"id":"2406.12667","title":"A Systematization of the Wagner Framework: Graph Theory Conjectures and Reinforcement Learning","created":"2024-06-18","cited_by_count":1,"area":"deeprl"},{"id":"2501.12703","title":"HEPPO-GAE: Hardware-Efficient Proximal Policy Optimization with Generalized Advantage Estimation","created":"2025-01-22","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":"2504.04366","title":"Solving Sokoban using Hierarchical Reinforcement Learning with Landmarks","created":"2025-04-06","cited_by_count":1,"area":"deeprl"},{"id":"2505.06319","title":"Reinforcement Learning for Game-Theoretic Resource Allocation on Graphs","created":"2025-05-08","cited_by_count":1,"area":"deeprl"},{"id":"2506.16352","title":"Data-Driven Policy Mapping for Safe RL-based Energy Management Systems","created":"2025-06-19","cited_by_count":1,"area":"deeprl"},{"id":"2507.02969","title":"Reinforcement Learning for Automated Cybersecurity Penetration Testing","created":"2025-06-30","cited_by_count":1,"area":"deeprl"},{"id":"2507.06825","title":"Artificial Generals Intelligence: Mastering Generals.io with Reinforcement Learning","created":"2025-07-09","cited_by_count":1,"area":"deeprl"},{"id":"2509.11233","title":"TransZero: Parallel Tree Expansion in MuZero using Transformer Networks","created":"2025-09-14","cited_by_count":1,"area":"deeprl"},{"id":"2510.16188","title":"Human-Allied Relational Reinforcement Learning","created":"2025-10-17","cited_by_count":1,"area":"deeprl"},{"id":"2512.17091","title":"Learning to Plan, Planning to Learn: Adaptive Hierarchical RL-MPC for Sample-Efficient Decision Making","created":"2025-12-18","cited_by_count":1,"area":"deeprl"},{"id":"2601.07637","title":"Reinforcement Learning for Micro-Level Claims Reserving","created":"2026-01-12","cited_by_count":1,"area":"deeprl"},{"id":"2601.14957","title":"Improving Regret Approximation for Unsupervised Dynamic Environment Generation","created":"2026-01-21","cited_by_count":1,"area":"deeprl"},{"id":"2602.12517","title":"Bench-MFG: A Benchmark Suite for Learning in Stationary Mean Field Games","created":"2026-02-13","cited_by_count":1,"area":"deeprl"},{"id":"2603.16279","title":"Agile Interception of a Flying Target using Competitive Reinforcement Learning","created":"2026-03-17","cited_by_count":1,"area":"deeprl"},{"id":"2402.06694","title":"Scaling Intelligent Agents in Combat Simulations for Wargaming","created":"2024-02-08","cited_by_count":0,"area":"deeprl"},{"id":"2405.14265","title":"Deep Reinforcement Learning for 5*5 Multiplayer Go","created":"2024-05-23","cited_by_count":0,"area":"deeprl"},{"id":"2405.18563","title":"No $D_{\\text{train}}$: Model-Agnostic Counterfactual Explanations Using Reinforcement Learning","created":"2024-05-28","cited_by_count":0,"area":"deeprl"},{"id":"2408.13328","title":"Localized Observation Abstraction Using Piecewise Linear Spatial Decay for Reinforcement Learning in Combat Simulations","created":"2024-08-23","cited_by_count":0,"area":"deeprl"},{"id":"2409.18626","title":"Refutation of Spectral Graph Theory Conjectures with Search Algorithms)","created":"2024-09-27","cited_by_count":0,"area":"deeprl"},{"id":"2410.11642","title":"Improve Value Estimation of Q Function and Reshape Reward with Monte Carlo Tree Search","created":"2024-10-15","cited_by_count":0,"area":"deeprl"},{"id":"2410.19880","title":"Implementing Deep Reinforcement Learning-Based Grid Voltage Control in Real-World Power Systems: Challenges and Insights","created":"2024-10-24","cited_by_count":0,"area":"deeprl"},{"id":"2410.23753","title":"Enhancing Chess Reinforcement Learning with Graph Representation","created":"2024-10-31","cited_by_count":0,"area":"deeprl"},{"id":"2503.10822","title":"Reinforcement Learning and Life Cycle Assessment for a Circular Economy -- Towards Progressive Computer Science","created":"2025-03-13","cited_by_count":0,"area":"deeprl"},{"id":"2505.21414","title":"A Framework for Adversarial Analysis of Decision Support Systems Prior to Deployment","created":"2025-05-27","cited_by_count":0,"area":"deeprl"},{"id":"2506.02205","title":"Bregman Centroid Guided Cross-Entropy Method","created":"2025-06-02","cited_by_count":0,"area":"deeprl"},{"id":"2508.07522","title":"Evolutionary Optimization of Deep Learning Agents for Sparrow Mahjong","created":"2025-08-11","cited_by_count":0,"area":"deeprl"},{"id":"2509.25402","title":"Parallel Heuristic Search as Inference for Actor-Critic Reinforcement Learning Models","created":"2025-09-29","cited_by_count":0,"area":"deeprl"},{"id":"2510.02896","title":"Global Convergence of Policy Gradient for Entropy Regularized Linear-Quadratic Control with Multiplicative Noise","created":"2025-10-03","cited_by_count":0,"area":"deeprl"},{"id":"2510.11933","title":"Efficient Restarts in Non-Stationary Model-Free Reinforcement Learning","created":"2025-10-13","cited_by_count":0,"area":"deeprl"},{"id":"2510.21888","title":"Computational Hardness of Reinforcement Learning with Partial $q^{\\pi}$-Realizability","created":"2025-10-24","cited_by_count":0,"area":"deeprl"},{"id":"2602.14559","title":"Fluid-Agent Reinforcement Learning","created":"2026-02-16","cited_by_count":0,"area":"deeprl"},{"id":"2602.18694","title":"In-Context Planning with Latent Temporal Abstractions","created":"2026-02-21","cited_by_count":0,"area":"deeprl"},{"id":"2603.06252","title":"Synthetic Monitoring Environments for Reinforcement Learning","created":"2026-03-06","cited_by_count":0,"area":"deeprl"},{"id":"2603.10289","title":"Quantum entanglement provides a competitive advantage in adversarial games","created":"2026-03-11","cited_by_count":0,"area":"deeprl"},{"id":"2605.06373","title":"Beyond the Independence Assumption: Finite-Sample Guarantees for Deep Q-Learning under $\\tau$-Mixing","created":"2026-05-07","cited_by_count":0,"area":"deeprl"},{"id":"2605.19235","title":"GAE Falls Short in Imperfect-Information Self-Play Reinforcement Learning","created":"2026-05-19","cited_by_count":0,"area":"deeprl"},{"id":"2606.23348","title":"Superhuman AI for Generals.io Using Self-Play Reinforcement Learning","created":"2026-06-22","cited_by_count":0,"area":"deeprl"},{"id":"2607.16177","title":"Physics-enhanced reinforcement learning for real-time optimal control of dynamical systems","created":"2026-07-17","cited_by_count":0,"area":"deeprl"},{"id":"2608.01133","title":"Policy Optimality Measurement for Multi-Vehicle Decision-Making: From Extrinsic Indicators to Intrinsic Quality","created":"2026-08-02","cited_by_count":0,"area":"deeprl"},{"id":"2608.02433","title":"Foundations of Reinforcement Learning and Control:Connections and New Perspectives","created":"2026-08-03","cited_by_count":0,"area":"deeprl"},{"id":"2610.07686","title":"BluffJAX: Adversarial Imperfect Information Games in JAX","created":"2026-10-06","cited_by_count":0,"area":"deeprl"},{"id":"2610.17391","title":"Learning to Play: Reinforcement Learning and Games","created":"2026-10-12","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}