{"total":95,"rows":[{"id":"2405.16158","title":"Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control","created":"2024-05-25","cited_by_count":108,"area":"deeprl"},{"id":"2407.04811","title":"Simplifying Deep Temporal Difference Learning","created":"2024-07-05","cited_by_count":78,"area":"deeprl"},{"id":"2410.09754","title":"SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning","created":"2024-10-13","cited_by_count":76,"area":"deeprl"},{"id":"2502.02316","title":"DIME:Diffusion-Based Maximum Entropy Reinforcement Learning","created":"2025-02-04","cited_by_count":58,"area":"diffusion"},{"id":"2502.00379","title":"Latent Action Learning Requires Supervision in the Presence of Distractors","created":"2025-02-01","cited_by_count":44,"area":null},{"id":"2502.15280","title":"Hyperspherical Normalization for Scalable Deep Reinforcement Learning","created":"2025-02-21","cited_by_count":38,"area":"deeprl"},{"id":"2502.11612","title":"Maximum Entropy Reinforcement Learning with Diffusion Policy","created":"2025-02-17","cited_by_count":34,"area":"diffusion"},{"id":"2411.04832","title":"Plasticity Loss in Deep Reinforcement Learning: A Survey","created":"2024-11-07","cited_by_count":24,"area":"deeprl"},{"id":"2505.23150","title":"Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners","created":"2025-05-29","cited_by_count":23,"area":null},{"id":"2509.06863","title":"floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL","created":"2025-09-08","cited_by_count":22,"area":"diffusion"},{"id":"2412.12089","title":"Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation","created":"2024-12-16","cited_by_count":20,"area":"deeprl"},{"id":"2502.07523","title":"Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization","created":"2025-02-11","cited_by_count":19,"area":"deeprl"},{"id":"2405.14956","title":"Interpretable and Editable Programmatic Tree Policies for Reinforcement Learning","created":"2024-05-23","cited_by_count":18,"area":"deeprl"},{"id":"2403.05996","title":"Dissecting Deep RL with High Update Ratios: Combatting Value Divergence","created":"2024-03-09","cited_by_count":17,"area":"deeprl"},{"id":"2509.25174","title":"XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning","created":"2025-09-29","cited_by_count":17,"area":"deeprl"},{"id":"2503.03660","title":"Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns","created":"2025-03-05","cited_by_count":16,"area":"deeprl"},{"id":"2410.11689","title":"BlendRL: A Framework for Merging Symbolic and Neural Policy Learning","created":"2024-10-15","cited_by_count":14,"area":"lr"},{"id":"2211.14296","title":"A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation","created":"2022-11-25","cited_by_count":13,"area":null},{"id":"2506.17204","title":"Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning","created":"2025-06-20","cited_by_count":11,"area":"deeprl"},{"id":"2410.08655","title":"FRASA: An End-to-End Reinforcement Learning Agent for Fall Recovery and Stand Up of Humanoid Robots","created":"2024-10-11","cited_by_count":10,"area":"deeprl"},{"id":"2106.15419","title":"Convergent and Efficient Deep Q Network Algorithm","created":"2021-06-29","cited_by_count":8,"area":null},{"id":"2503.08375","title":"Gait in Eight: Efficient On-Robot Learning for Omnidirectional Quadruped Locomotion","created":"2025-03-11","cited_by_count":8,"area":"deeprl"},{"id":"2505.15345","title":"Hadamax Encoding: Elevating Performance in Model-Free Atari","created":"2025-05-21","cited_by_count":7,"area":"deeprl"},{"id":"2111.12673","title":"Adaptively Calibrated Critic Estimates for Deep Reinforcement Learning","created":"2021-11-24","cited_by_count":6,"area":null},{"id":"2310.19527","title":"On the Theory of Risk-Aware Agents: Bridging Actor-Critic and Economics","created":"2023-10-30","cited_by_count":6,"area":null},{"id":"2403.02107","title":"Iterated $Q$-Network: Beyond One-Step Bellman Updates in Deep Reinforcement Learning","created":"2024-03-04","cited_by_count":6,"area":"deeprl"},{"id":"2503.01437","title":"Eau De $Q$-Network: Adaptive Distillation of Neural Networks in Deep Reinforcement Learning","created":"2025-03-03","cited_by_count":6,"area":"deeprl"},{"id":"2601.19707","title":"Scalable Exploration for High-Dimensional Continuous Control via Value-Guided Flow","created":"2026-01-27","cited_by_count":5,"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":"2506.04398","title":"Bridging the Performance Gap Between Target-Free and Target-Based Reinforcement Learning","created":"2025-06-04","cited_by_count":4,"area":"deeprl"},{"id":"2209.08898","title":"Batch Layer Normalization, A new normalization layer for CNNs and RNN","created":"2022-09-19","cited_by_count":3,"area":null},{"id":"2405.16195","title":"Adaptive $Q$-Network: On-the-fly Target Selection for Deep Reinforcement Learning","created":"2024-05-25","cited_by_count":3,"area":"deeprl"},{"id":"2506.06361","title":"Tactile MNIST: Benchmarking Active Tactile Perception","created":"2025-06-03","cited_by_count":3,"area":null},{"id":"2602.18291","title":"Diffusing to Coordinate: Efficient Online Multi-Agent Diffusion Policies","created":"2026-02-20","cited_by_count":3,"area":"diffusion"},{"id":"2605.30749","title":"FLAG: Flow Policy MaxEnt-RL by Latent Augmented Guidance","created":"2026-05-29","cited_by_count":3,"area":"deeprl"},{"id":"2405.15421","title":"Model-free reinforcement learning with noisy actions for automated experimental control in optics","created":"2024-05-24","cited_by_count":2,"area":"deeprl"},{"id":"2410.14957","title":"Offline-to-online Reinforcement Learning for Image-based Grasping with Scarce Demonstrations","created":"2024-10-19","cited_by_count":2,"area":"offlinerl"},{"id":"2505.00787","title":"Constructing an Optimal Behavior Basis for the Option Keyboard","created":"2025-05-01","cited_by_count":2,"area":"deeprl"},{"id":"2505.06182","title":"Apple: Toward General Active Perception via Reinforcement Learning","created":"2025-05-09","cited_by_count":2,"area":"deeprl"},{"id":"2506.22174","title":"ASVSim (AirSim for Surface Vehicles): A High-Fidelity Simulation Framework for Autonomous Surface Vehicle Research","created":"2025-06-27","cited_by_count":2,"area":null},{"id":"2508.06871","title":"Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning","created":"2025-08-09","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":"2510.10332","title":"Towards Safe Maneuvering of Double-Ackermann-Steering Robots with a Soft Actor-Critic Framework","created":"2025-10-11","cited_by_count":2,"area":"deeprl"},{"id":"2601.06133","title":"A Review of Online Diffusion Policy RL Algorithms for Scalable Robotic Control","created":"2026-01-05","cited_by_count":2,"area":"diffusion"},{"id":"2602.11800","title":"Temporal Difference Learning with Constrained Initial Representations","created":"2026-02-12","cited_by_count":2,"area":"deeprl"},{"id":"2604.09159","title":"Truncated Rectified Flow Policy for Reinforcement Learning with One-Step Sampling","created":"2026-04-10","cited_by_count":2,"area":"diffusion"},{"id":"2403.04453","title":"Efficient Off-Policy Learning for High-Dimensional Action Spaces","created":"2024-03-07","cited_by_count":1,"area":"deeprl"},{"id":"2404.15617","title":"A Differential and Pointwise Control Approach to Reinforcement Learning","created":"2024-04-24","cited_by_count":1,"area":"deeprl"},{"id":"2405.00383","title":"Learning Tactile Insertion in the Real World","created":"2024-05-01","cited_by_count":1,"area":"deeprl"},{"id":"2406.09079","title":"Hadamard Representation: Scaffolding Performance Across Model-free RL","created":"2024-06-13","cited_by_count":1,"area":"deeprl"},{"id":"2502.02382","title":"Circular Microalgae-Based Carbon Control for Net Zero","created":"2025-02-04","cited_by_count":1,"area":null},{"id":"2502.11949","title":"Massively Scaling Explicit Policy-conditioned Value Functions","created":"2025-02-17","cited_by_count":1,"area":"deeprl"},{"id":"2506.03758","title":"Scaling CrossQ with Weight Normalization","created":"2025-06-04","cited_by_count":1,"area":"deeprl"},{"id":"2506.18627","title":"Multi-Agent Reinforcement Learning for Inverse Design in Photonic Integrated Circuits","created":"2025-06-23","cited_by_count":1,"area":null},{"id":"2507.11486","title":"Exploring the robustness of TractOracle methods in RL-based tractography","created":"2025-07-15","cited_by_count":1,"area":null},{"id":"2508.03194","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2508.07746","title":"A Tutorial: An Intuitive Explanation of Offline Reinforcement Learning Theory","created":"2025-08-11","cited_by_count":1,"area":"offlinerl"},{"id":"2510.08768","title":"Zero-Shot Policy Transfer in Reinforcement Learning using Buckingham's Pi Theorem","created":"2025-10-09","cited_by_count":1,"area":"deeprl"},{"id":"2510.12096","title":"Rethinking the Role of Dynamic Sparse Training for Scalable Deep Reinforcement Learning","created":"2025-10-14","cited_by_count":1,"area":"deeprl"},{"id":"2512.12230","title":"Learning to Get Up Across Morphologies: Zero-Shot Recovery with a Unified Humanoid Policy","created":"2025-12-13","cited_by_count":1,"area":null},{"id":"2601.20765","title":"Less is More: Clustered Cross-Covariance Control for Offline RL","created":"2026-01-28","cited_by_count":1,"area":"offlinerl"},{"id":"2601.21363","title":"Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid Control","created":"2026-01-29","cited_by_count":1,"area":"deeprl"},{"id":"2602.05619","title":"Mode-Dependent Rectification for Stable PPO Training","created":"2026-02-05","cited_by_count":1,"area":"deeprl"},{"id":"2602.14726","title":"ManeuverNet: A Soft Actor-Critic Framework for Precise Maneuvering of Double-Ackermann-Steering Robots with Optimized Reward Functions","created":"2026-02-16","cited_by_count":1,"area":"deeprl"},{"id":"2603.12612","title":"FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Control","created":"2026-03-13","cited_by_count":1,"area":"deeprl"},{"id":"2605.08733","title":"Generative Actor-Critic with Soft Bridge Policies","created":"2026-05-09","cited_by_count":1,"area":"deeprl"},{"id":"2605.10734","title":"XQCfD: Accelerating Fast Actor-Critic Algorithms with Prior Data and Prior Policies","created":"2026-05-11","cited_by_count":1,"area":"deeprl"},{"id":"2605.11711","title":"Debiased Model-based Representations for Sample-efficient Continuous Control","created":"2026-05-12","cited_by_count":1,"area":"deeprl"},{"id":"2605.21214","title":"Behavior-Consistent Deep Reinforcement Learning","created":"2026-05-20","cited_by_count":1,"area":"deeprl"},{"id":"2104.07361","title":"Scale Invariant Monte Carlo under Linear Function Approximation with Curvature based step-size","created":"2021-04-15","cited_by_count":0,"area":null},{"id":"2412.20537","title":"Diminishing Return of Value Expansion Methods","created":"2024-12-29","cited_by_count":0,"area":"deeprl"},{"id":"2503.05818","title":"Closing the Intent-to-Behavior Gap via Fulfillment Priority Logic","created":"2025-03-04","cited_by_count":0,"area":"deeprl"},{"id":"2506.16608","title":"Distributions as Actions: A Unified Framework for Diverse Action Spaces","created":"2025-06-19","cited_by_count":0,"area":"deeprl"},{"id":"2509.23750","title":"An Investigation of Batch Normalization in Off-Policy Actor-Critic Algorithms","created":"2025-09-28","cited_by_count":0,"area":"deeprl"},{"id":"2510.01457","title":"A Forensic Analysis of Synthetic Data in RL: Diagnosing and Solving Algorithmic Failures in Model-Based Policy Optimization","created":"2025-10-01","cited_by_count":0,"area":"deeprl"},{"id":"2510.18828","title":"Actor-Free Continuous Control via Structurally Maximizable Q-Functions","created":"2025-10-21","cited_by_count":0,"area":"deeprl"},{"id":"2603.07110","title":"Learning From Failures: Efficient Reinforcement Learning Control with Episodic Memory","created":"2026-03-07","cited_by_count":0,"area":"deeprl"},{"id":"2604.16871","title":"GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learning","created":"2026-04-18","cited_by_count":0,"area":"lr"},{"id":"2604.18978","title":"Low-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning","created":"2026-04-21","cited_by_count":0,"area":"deeprl"},{"id":"2605.10236","title":"When Does Non-Uniform Replay Matter in Reinforcement Learning?","created":"2026-05-11","cited_by_count":0,"area":"deeprl"},{"id":"2605.14026","title":"R2R2: Robust Representation for Intensive Experience Reuse via Redundancy Reduction in Self-Predictive Learning","created":"2026-05-13","cited_by_count":0,"area":"deeprl"},{"id":"2605.21282","title":"Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent","created":"2026-05-20","cited_by_count":0,"area":"deeprl"},{"id":"2605.27385","title":"Personalized Observation Normalization for Federated Reinforcement Learning in Simulation Environments with Heterogeneity","created":"2026-04-10","cited_by_count":0,"area":"deeprl"},{"id":"2606.00313","title":"DRL-Based Pose Control for Double-Ackermann Robots Under Actuation Uncertainties","created":"2026-05-29","cited_by_count":0,"area":"deeprl"},{"id":"2606.10448","title":"Mitigating Bias in Low-SNR Financial Reinforcement Learning via Quantum Representations","created":"2026-06-09","cited_by_count":0,"area":"deeprl"},{"id":"2606.31291","title":"Deep Reinforcement Learning for Spacecraft Attitude Control During Atmospheric Re-Entry","created":"2026-06-30","cited_by_count":0,"area":"deeprl"},{"id":"2607.24320","title":"Continual-RL for Generalization in Autonomous Racing on the RoboRacer Platform","created":"2026-07-27","cited_by_count":0,"area":"deeprl"},{"id":"2608.07335","title":"A Progressive Design Study of Visual Encoders and Value Estimation for Replay-Free Parallelized Q-Learning","created":"2026-08-07","cited_by_count":0,"area":"deeprl"},{"id":"2608.07870","title":"V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control","created":"2026-08-08","cited_by_count":0,"area":"deeprl"},{"id":"2608.12063","title":"Learning Loco-Manipulation From SMPC Demonstrations With Sparse Offline-to-Online RL","created":"2026-08-12","cited_by_count":0,"area":"offlinerl"},{"id":"2608.16607","title":"Interactive Whole Slide Images for RL-based Tumour Segmentation","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.06421","title":"On BatchNorm Forward Modes in Value-Based Reinforcement Learning","created":"2026-09-06","cited_by_count":0,"area":"deeprl"},{"id":"2609.20300","title":"Improving Generalization and Robustness in Offline Reinforcement Learning via Boundary-Aware Data Augmentation","created":"2026-08-22","cited_by_count":0,"area":"offlinerl"},{"id":"2609.32819","title":"Rank Collapse Is Recoverable, Growing $|Q|$ Is Not: Out-of-Sample Early Warning for Value Divergence in High-UTD Soft Actor-Critic","created":"2026-09-26","cited_by_count":0,"area":"deeprl"},{"id":"2610.01882","title":"Flowing Faster to Coordinate: One-Step Online Multi-Agent Flow Policies","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}