{"total":19,"rows":[{"id":"2406.18293","title":"Combining Automated Optimisation of Hyperparameters and Reward Shape","created":"2024-06-26","cited_by_count":5,"area":"deeprl"},{"id":"2404.08233","title":"Generalized Population-Based Training for Hyperparameter Optimization in Reinforcement Learning","created":"2024-04-12","cited_by_count":4,"area":"deeprl"},{"id":"2410.14038","title":"Sliding Puzzles Gym: A Scalable Benchmark for State Representation in Visual Reinforcement Learning","created":"2024-10-17","cited_by_count":3,"area":"deeprl"},{"id":"2508.04078","title":"RLGS: Reinforcement Learning-Based Adaptive Hyperparameter Tuning for Gaussian Splatting","created":"2025-08-06","cited_by_count":3,"area":"deeprl"},{"id":"2512.06244","title":"Auto-exploration for online reinforcement learning","created":"2025-12-06","cited_by_count":3,"area":"deeprl"},{"id":"2503.06101","title":"ULTHO: Ultra-Lightweight yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning","created":"2025-03-08","cited_by_count":1,"area":"deeprl"},{"id":"2506.03225","title":"Multiple-Frequencies Population-Based Training","created":"2025-06-03","cited_by_count":1,"area":"deeprl"},{"id":"2506.15051","title":"Sequential Policy Gradient for Adaptive Hyperparameter Optimization","created":"2025-06-18","cited_by_count":1,"area":"deeprl"},{"id":"2508.16807","title":"Autonomous UAV Flight Navigation in Confined Spaces: A Reinforcement Learning Approach","created":"2025-08-22","cited_by_count":1,"area":"deeprl"},{"id":"2512.03805","title":"Deep Reinforcement Learning for Dynamic Algorithm Configuration: A Case Study on Optimizing OneMax with the (1+($\\lambda$,$\\lambda$))-GA","created":"2025-12-03","cited_by_count":1,"area":"deeprl"},{"id":"2603.07300","title":"AutoResearch-RL: Perpetual Self-Evaluating Reinforcement Learning Agents for Autonomous Neural Architecture Discovery","created":"2026-03-07","cited_by_count":1,"area":"deeprl"},{"id":"2408.04046","title":"Learning Rate-Free Reinforcement Learning: A Case for Model Selection with Non-Stationary Objectives","created":"2024-08-07","cited_by_count":0,"area":"deeprl"},{"id":"2410.12598","title":"Dynamic Learning Rate for Deep Reinforcement Learning: A Bandit Approach","created":"2024-10-16","cited_by_count":0,"area":"deeprl"},{"id":"2504.19382","title":"HyperController: A Hyperparameter Controller for Fast and Stable Training of Reinforcement Learning Neural Networks","created":"2025-04-27","cited_by_count":0,"area":"deeprl"},{"id":"2505.15754","title":"Improving planning and MBRL with temporally-extended actions","created":"2025-05-21","cited_by_count":0,"area":"deeprl"},{"id":"2601.05205","title":"EARL: Energy-Aware Optimization of Liquid State Machines for Pervasive AI","created":"2026-01-08","cited_by_count":0,"area":"deeprl"},{"id":"2606.10129","title":"Discovering Interpretable Multi-Parameter Control Policies for Evolutionary Algorithms Using Deep Reinforcement Learning","created":"2026-06-08","cited_by_count":0,"area":"deeprl"},{"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":"2610.15691","title":"FARL: A Fully Automated Pipeline of RL Interface and Solver Design","created":"2026-10-11","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}