{"total":26,"rows":[{"id":"2402.18762","title":"Disentangling the Causes of Plasticity Loss in Neural Networks","created":"2024-02-29","cited_by_count":86,"area":"deeprl"},{"id":"2410.14606","title":"Streaming Deep Reinforcement Learning Finally Works","created":"2024-10-18","cited_by_count":25,"area":"deeprl"},{"id":"2405.09999","title":"Reward Centering","created":"2024-05-16","cited_by_count":16,"area":"deeprl"},{"id":"2412.07165","title":"A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning","created":"2024-12-10","cited_by_count":15,"area":"deeprl"},{"id":"2408.10932","title":"The Evolution of Reinforcement Learning in Quantitative Finance: A Survey","created":"2024-08-20","cited_by_count":11,"area":"deeprl"},{"id":"2402.06819","title":"Monitored Markov Decision Processes","created":"2024-02-09","cited_by_count":10,"area":"deeprl"},{"id":"2509.22442","title":"Learning to Ball: Composing Policies for Long-Horizon Basketball Moves","created":"2025-09-26","cited_by_count":6,"area":"deeprl"},{"id":"2502.20265","title":"On the Importance of Reward Design in Reinforcement Learning-based Dynamic Algorithm Configuration: A Case Study on OneMax with (1+($\\lambda$,$\\lambda$))-GA","created":"2025-02-27","cited_by_count":5,"area":"deeprl"},{"id":"2407.18143","title":"Maximum Entropy On-Policy Actor-Critic via Entropy Advantage Estimation","created":"2024-07-25","cited_by_count":4,"area":"deeprl"},{"id":"2406.10242","title":"Physics-Guided Actor-Critic Reinforcement Learning for Swimming in Turbulence","created":"2024-06-05","cited_by_count":2,"area":"deeprl"},{"id":"2602.06746","title":"Semantically Labelled Automata for Multi-Task Reinforcement Learning with LTL Instructions","created":"2026-02-06","cited_by_count":2,"area":"deeprl"},{"id":"2406.01838","title":"Learning the Target Network in Function Space","created":"2024-06-03","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":"2607.16534","title":"Building2Building: A Large Scale Benchmark for Generalizable Real-World Reinforcement Learning","created":"2026-07-17","cited_by_count":1,"area":"deeprl"},{"id":"2505.07832","title":"A General Approach of Automated Environment Design for Learning the Optimal Power Flow","created":"2025-05-01","cited_by_count":0,"area":"deeprl"},{"id":"2604.26150","title":"Reinforcement Learning for Public Safety Power Shutoffs Under Decision-Dependent Uncertainty and Nonlinear Wildfire Ignition Models","created":"2026-04-28","cited_by_count":0,"area":"deeprl"},{"id":"2605.04368","title":"Extending Differential Temporal Difference Methods for Episodic Problems","created":"2026-05-06","cited_by_count":0,"area":"deeprl"},{"id":"2605.11473","title":"TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing","created":"2026-05-12","cited_by_count":0,"area":"deeprl"},{"id":"2606.29806","title":"Accelerating Q-learning through Efficient Value-Sharing across Actions","created":"2026-06-29","cited_by_count":0,"area":"deeprl"},{"id":"2607.01880","title":"Learning the Supports for Categorical Critic in Reinforcement Learning","created":"2026-07-02","cited_by_count":0,"area":"deeprl"},{"id":"2608.04305","title":"Adaptive Finite-Budget Training for CVaR Risk-Aware Q-Learning","created":"2026-08-05","cited_by_count":0,"area":"deeprl"},{"id":"2608.12256","title":"SelectLight: Learning to Select Signal Plans Generated by Distributed Model Predictive Control for Urban Traffic Networks","created":"2026-08-12","cited_by_count":0,"area":"deeprl"},{"id":"2608.26481","title":"Shared Actors Need Not Share Critics: Effects of Value Mismatch in Parallel Reinforcement Learning","created":"2026-08-27","cited_by_count":0,"area":"deeprl"},{"id":"2609.34695","title":"Sufficiency of Zeroth-Order Reward Shaping for Policy Gradient in Stabilization Control","created":"2026-09-28","cited_by_count":0,"area":"deeprl"},{"id":"2610.02074","title":"Homomorphic Advantage Operator: Stabilizing Reinforcement Learning Under Fully Homomorphic Encryption Constraints","created":"2026-10-01","cited_by_count":0,"area":"deeprl"},{"id":"2610.02545","title":"Reward Inflation: A Healthy Stimulus for Reinforcement Learning","created":"2026-10-01","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}