{"total":46,"rows":[{"id":"2412.12089","title":"Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation","created":"2024-12-16","cited_by_count":20,"area":"deeprl"},{"id":"2411.15370","title":"Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers","created":"2024-11-22","cited_by_count":18,"area":"deeprl"},{"id":"2405.02235","title":"Learning Optimal Deterministic Policies with Stochastic Policy Gradients","created":"2024-05-03","cited_by_count":12,"area":"deeprl"},{"id":"2405.19697","title":"Bilevel reinforcement learning via the development of hyper-gradient without lower-level convexity","created":"2024-05-30","cited_by_count":10,"area":"deeprl"},{"id":"2410.22093","title":"PC-Gym: Benchmark Environments For Process Control Problems","created":"2024-10-29","cited_by_count":10,"area":"deeprl"},{"id":"2501.16918","title":"On Rollouts in Model-Based Reinforcement Learning","created":"2025-01-28","cited_by_count":10,"area":"deeprl"},{"id":"2405.18221","title":"Recurrent Natural Policy Gradient for POMDPs","created":"2024-05-28","cited_by_count":8,"area":"deeprl"},{"id":"2501.11533","title":"The impact of intrinsic rewards on exploration in Reinforcement Learning","created":"2025-01-20","cited_by_count":8,"area":"deeprl"},{"id":"2503.00799","title":"On Generalization Across Environments In Multi-Objective Reinforcement Learning","created":"2025-03-02","cited_by_count":8,"area":"deeprl"},{"id":"2405.13136","title":"Towards Principled, Practical Policy Gradient for Bandits and Tabular MDPs","created":"2024-05-21","cited_by_count":7,"area":"deeprl"},{"id":"2506.05615","title":"When Maximum Entropy Misleads Policy Optimization","created":"2025-06-05","cited_by_count":7,"area":"deeprl"},{"id":"2506.07085","title":"State Entropy Regularization for Robust Reinforcement Learning","created":"2025-06-08","cited_by_count":6,"area":"deeprl"},{"id":"2601.15353","title":"Reinforcement Learning in the Real World: A Survey of Statistical Challenges and Future Directions","created":"2026-01-21","cited_by_count":5,"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":"2407.18143","title":"Maximum Entropy On-Policy Actor-Critic via Entropy Advantage Estimation","created":"2024-07-25","cited_by_count":4,"area":"deeprl"},{"id":"2408.00309","title":"Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning","created":"2024-08-01","cited_by_count":4,"area":"deeprl"},{"id":"2402.00162","title":"Behind the Myth of Exploration in Policy Gradients","created":"2024-01-31","cited_by_count":3,"area":"deeprl"},{"id":"2406.17334","title":"Joint Admission Control and Resource Allocation of Virtual Network Embedding via Hierarchical Deep Reinforcement Learning","created":"2024-06-25","cited_by_count":3,"area":"deeprl"},{"id":"2406.19825","title":"Reinforcement Learning for Efficient Design and Control Co-optimisation of Energy Systems","created":"2024-06-28","cited_by_count":3,"area":"deeprl"},{"id":"2412.06655","title":"Off-Policy Maximum Entropy RL with Future State and Action Visitation Measures","created":"2024-12-09","cited_by_count":3,"area":"deeprl"},{"id":"2501.17115","title":"Evidence on the Regularisation Properties of Maximum-Entropy Reinforcement Learning","created":"2025-01-28","cited_by_count":3,"area":"deeprl"},{"id":"2510.25529","title":"Off-policy Reinforcement Learning with Model-based Exploration Augmentation","created":"2025-10-29","cited_by_count":3,"area":"deeprl"},{"id":"2511.22581","title":"High entropy leads to symmetry-equivariant policies in Dec-POMDPs","created":"2025-11-27","cited_by_count":3,"area":"deeprl"},{"id":"2401.15196","title":"Regularized Q-Learning with Linear Function Approximation","created":"2024-01-26","cited_by_count":2,"area":"deeprl"},{"id":"2408.07245","title":"q-exponential family for policy optimization","created":"2024-08-14","cited_by_count":2,"area":"deeprl"},{"id":"2510.08526","title":"Convergence Theorems for Entropy-Regularized and Distributional Reinforcement Learning","created":"2025-10-09","cited_by_count":2,"area":"deeprl"},{"id":"2510.12334","title":"Finite-time Convergence Analysis of Actor-Critic with Evolving Reward","created":"2025-10-14","cited_by_count":2,"area":"deeprl"},{"id":"2401.12508","title":"On the Stochastic (Variance-Reduced) Proximal Gradient Method for Regularized Expected Reward Optimization","created":"2024-01-23","cited_by_count":1,"area":"deeprl"},{"id":"2405.11457","title":"Deep Dive into Model-free Reinforcement Learning for Biological and Robotic Systems: Theory and Practice","created":"2024-05-19","cited_by_count":1,"area":"deeprl"},{"id":"2406.04163","title":"Optimal Rates of Convergence for Entropy Regularization in Discounted Markov Decision Processes","created":"2024-06-06","cited_by_count":1,"area":"deeprl"},{"id":"2411.14117","title":"Umbrella Reinforcement Learning -- computationally efficient tool for hard non-linear problems","created":"2024-11-21","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":"2605.09157","title":"Revisiting Mixture Policies in Entropy-Regularized Actor-Critic","created":"2026-05-09","cited_by_count":1,"area":"deeprl"},{"id":"2506.08029","title":"Inverse Design in Distributed Circuits Using Single-Step Reinforcement Learning","created":"2025-06-02","cited_by_count":0,"area":"deeprl"},{"id":"2506.15700","title":"Contraction-Aware Reinforcement Learning for Nonlinear Control with Statistical Robustness","created":"2025-05-28","cited_by_count":0,"area":"deeprl"},{"id":"2508.21314","title":"Convergence of regularized agent-state-based Q-learning in POMDPs","created":"2025-08-29","cited_by_count":0,"area":"deeprl"},{"id":"2509.02737","title":"Imitate Optimal Policy: Prevail and Induce Action Collapse in Policy Gradient","created":"2025-09-02","cited_by_count":0,"area":"deeprl"},{"id":"2509.20509","title":"Complexity-Regularized Proximal Policy Optimization","created":"2025-09-24","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":"2510.25311","title":"Dense and Diverse Goal Coverage in Multi Goal Reinforcement Learning","created":"2025-10-29","cited_by_count":0,"area":"deeprl"},{"id":"2601.00007","title":"Yahtzee: Reinforcement Learning Techniques for Stochastic Combinatorial Games","created":"2025-12-18","cited_by_count":0,"area":"deeprl"},{"id":"2602.10838","title":"Mirror descent actor-critic methods for entropy regularised MDPs in general spaces: stability and convergence","created":"2026-02-11","cited_by_count":0,"area":"deeprl"},{"id":"2603.18965","title":"Maximum-Entropy Exploration with Future State-Action Visitation Measures","created":"2026-03-19","cited_by_count":0,"area":"deeprl"},{"id":"2605.10377","title":"PC3D: Zero-Shot Cooperation Across Variable Rosters via Personalized Context Distillation","created":"2026-05-11","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":"2607.17316","title":"Rationalizing Boltzmann Rationality: An Axiomatic Characterization of Entropy-Regularized Policies","created":"2026-07-19","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}