{"total":15,"rows":[{"id":"2601.11087","title":"PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models","created":"2026-01-16","cited_by_count":17,"area":"deeprl"},{"id":"2502.04327","title":"Value-Based Deep RL Scales Predictably","created":"2025-02-06","cited_by_count":15,"area":"deeprl"},{"id":"2507.11019","title":"Relative Entropy Pathwise Policy Optimization","created":"2025-07-15","cited_by_count":7,"area":"deeprl"},{"id":"2508.14881","title":"Compute-Optimal Scaling for Value-Based Deep RL","created":"2025-08-20","cited_by_count":6,"area":"deeprl"},{"id":"2601.21669","title":"Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling","created":"2026-01-29","cited_by_count":5,"area":"deeprl"},{"id":"2506.03066","title":"Sign-SZPO: Provable Preference-based Reinforcement Learning with an Unknown Link Function","created":"2025-06-03","cited_by_count":4,"area":"deeprl"},{"id":"2608.07418","title":"ResidencyRL: Reinforcement Learning in Simulated Clinical Environments","created":"2026-08-07","cited_by_count":3,"area":"deeprl"},{"id":"2406.07877","title":"Hierarchical Reinforcement Learning for Swarm Confrontation with High Uncertainty","created":"2024-06-12","cited_by_count":2,"area":"deeprl"},{"id":"2410.06213","title":"RL, but don't do anything I wouldn't do","created":"2024-10-08","cited_by_count":2,"area":"deeprl"},{"id":"2602.08092","title":"Objective Decoupling in Social Reinforcement Learning: Recovering Ground Truth from Sycophantic Majorities","created":"2026-02-08","cited_by_count":2,"area":"deeprl"},{"id":"2609.27033","title":"WTF?! Simulation-Free Reinforcement Learning with Wasserstein-Tilted Flow Maps","created":"2026-09-22","cited_by_count":1,"area":"deeprl"},{"id":"2604.04251","title":"MC-CPO: Mastery-Conditioned Constrained Policy Optimization for Pedagogically Safe Intelligent Tutoring Systems","created":"2026-04-05","cited_by_count":0,"area":"deeprl"},{"id":"2605.25739","title":"The Behavioral Credibility Trilemma: When Calibrated Autonomy Becomes Impossible","created":"2026-05-25","cited_by_count":0,"area":"deeprl"},{"id":"2606.11982","title":"PAWS: Preference Learning with Advantage-Weighted Segments","created":"2026-06-10","cited_by_count":0,"area":"deeprl"},{"id":"2610.19617","title":"Instruction-Conditioned Motion Control for Robotic Arms: Language-to-Code Decomposition and Reinforcement Learning","created":"2026-10-14","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}