{"total":68,"rows":[{"id":"2505.15134","title":"The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning","created":"2025-05-21","cited_by_count":166,"area":"lr"},{"id":"2210.00580","title":"GFlowNets and variational inference","created":"2022-10-02","cited_by_count":106,"area":null},{"id":"2211.07937","title":"An Improved Analysis of (Variance-Reduced) Policy Gradient and Natural Policy Gradient Methods","created":"2022-11-15","cited_by_count":68,"area":null},{"id":"2209.07089","title":"Constrained Update Projection Approach to Safe Policy Optimization","created":"2022-09-15","cited_by_count":58,"area":null},{"id":"2108.08612","title":"Settling the Variance of Multi-Agent Policy Gradients","created":"2021-08-19","cited_by_count":45,"area":null},{"id":"2506.07976","title":"Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction","created":"2025-06-09","cited_by_count":34,"area":"lr"},{"id":"2102.10264","title":"On Proximal Policy Optimization's Heavy-tailed Gradients","created":"2021-02-20","cited_by_count":31,"area":null},{"id":"2506.02864","title":"BNPO: Beta Normalization Policy Optimization","created":"2025-06-03","cited_by_count":28,"area":"lr"},{"id":"2505.04671","title":"Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewards","created":"2025-05-07","cited_by_count":27,"area":"lr"},{"id":"2110.10116","title":"On the Global Optimum Convergence of Momentum-based Policy Gradient","created":"2021-10-19","cited_by_count":26,"area":null},{"id":"2210.01542","title":"Hyperbolic Deep Reinforcement Learning","created":"2022-10-04","cited_by_count":25,"area":null},{"id":"2301.06276","title":"The Role of Baselines in Policy Gradient Optimization","created":"2023-01-16","cited_by_count":25,"area":null},{"id":"2305.04866","title":"Causal Policy Gradient for Whole-Body Mobile Manipulation","created":"2023-05-04","cited_by_count":21,"area":null},{"id":"2202.07565","title":"CUP: A Conservative Update Policy Algorithm for Safe Reinforcement Learning","created":"2022-02-15","cited_by_count":20,"area":null},{"id":"2210.11931","title":"Deep Reinforcement Learning for Inverse Inorganic Materials Design","created":"2022-10-21","cited_by_count":19,"area":null},{"id":"2306.16021","title":"Structure in Deep Reinforcement Learning: A Survey and Open Problems","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2410.23916","title":"Transformer-based Model Predictive Control: Trajectory Optimization via Sequence Modeling","created":"2024-10-31","cited_by_count":16,"area":null},{"id":"2103.17258","title":"Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning","created":"2021-03-31","cited_by_count":15,"area":null},{"id":"2212.09010","title":"Risk-Sensitive Reinforcement Learning with Exponential Criteria","created":"2022-12-18","cited_by_count":15,"area":null},{"id":"2208.04055","title":"Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions","created":"2022-08-08","cited_by_count":14,"area":null},{"id":"2306.16803","title":"Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis","created":"2023-06-29","cited_by_count":13,"area":null},{"id":"2402.17235","title":"Stochastic Gradient Succeeds for Bandits","created":"2024-02-27","cited_by_count":10,"area":null},{"id":"2102.10362","title":"Factored Policy Gradients: Leveraging Structure for Efficient Learning in MOMDPs","created":"2021-02-20","cited_by_count":8,"area":null},{"id":"2312.08884","title":"Global Rewards in Multi-Agent Deep Reinforcement Learning for Autonomous Mobility on Demand Systems","created":"2023-12-14","cited_by_count":8,"area":null},{"id":"2107.12216","title":"Hindsight Value Function for Variance Reduction in Stochastic Dynamic Environment","created":"2021-07-26","cited_by_count":7,"area":null},{"id":"2312.02438","title":"Adaptive Instrument Design for Indirect Experiments","created":"2023-12-05","cited_by_count":6,"area":null},{"id":"2512.20576","title":"Performative Policy Gradient: Optimality in Performative Reinforcement Learning","created":"2025-12-23","cited_by_count":6,"area":"deeprl"},{"id":"2106.13125","title":"Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation","created":"2021-06-24","cited_by_count":5,"area":null},{"id":"2112.12740","title":"Learning Cooperative Multi-Agent Policies with Partial Reward Decoupling","created":"2021-12-23","cited_by_count":5,"area":null},{"id":"2510.22686","title":"FlowCritic: Bridging Value Estimation with Flow Matching in Reinforcement Learning","created":"2025-10-26","cited_by_count":5,"area":"diffusion"},{"id":"2206.06827","title":"Variance Reduction for Policy-Gradient Methods via Empirical Variance Minimization","created":"2022-06-14","cited_by_count":4,"area":null},{"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":"2502.15968","title":"Enhancing PPO with Trajectory-Aware Hybrid Policies","created":"2025-02-21","cited_by_count":4,"area":"deeprl"},{"id":"2109.08512","title":"Soft Actor-Critic With Integer Actions","created":"2021-09-17","cited_by_count":3,"area":null},{"id":"2203.15413","title":"Deep Reinforcement Learning for Data-Driven Adaptive Scanning in Ptychography","created":"2022-03-29","cited_by_count":3,"area":null},{"id":"2204.09603","title":"Comparing Deep Reinforcement Learning Algorithms in Two-Echelon Supply Chains","created":"2022-04-20","cited_by_count":3,"area":null},{"id":"2301.13236","title":"Policy Gradient with Tree Expansion","created":"2023-01-30","cited_by_count":3,"area":null},{"id":"2302.02299","title":"Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization","created":"2023-02-05","cited_by_count":3,"area":null},{"id":"2505.01900","title":"CAMOUFLAGE: Exploiting Misinformation Detection Systems Through LLM-driven Adversarial Claim Transformation","created":"2025-05-03","cited_by_count":3,"area":null},{"id":"2201.05819","title":"Interpretable and Effective Reinforcement Learning for Attacking against Graph-based Rumor Detection","created":"2022-01-15","cited_by_count":2,"area":null},{"id":"2303.01346","title":"Co-learning Planning and Control Policies Constrained by Differentiable Logic Specifications","created":"2023-03-02","cited_by_count":2,"area":null},{"id":"2503.05696","title":"A Multi-Fidelity Control Variate Approach for Policy Gradient Estimation","created":"2025-03-07","cited_by_count":2,"area":"deeprl"},{"id":"2606.06080","title":"On Advantage Estimates for Max@K Policy Gradients","created":"2026-06-04","cited_by_count":2,"area":"lr"},{"id":"2607.13394","title":"GFlowRL: Scaling Distribution-Matching RL to Large Language Models","created":"2026-07-15","cited_by_count":2,"area":"lr"},{"id":"2609.36939","title":"SCA: Spatial Credit Assignment for Reinforcement Learning of GUI Agents","created":"2026-09-29","cited_by_count":2,"area":"agents"},{"id":"2107.04987","title":"Coordinate-wise Control Variates for Deep Policy Gradients","created":"2021-07-11","cited_by_count":1,"area":null},{"id":"2208.12341","title":"Variance Reduction based Experience Replay for Policy Optimization","created":"2022-08-25","cited_by_count":1,"area":null},{"id":"2209.13966","title":"SoftTreeMax: Policy Gradient with Tree Search","created":"2022-09-28","cited_by_count":1,"area":null},{"id":"2302.00533","title":"Distillation Policy Optimization","created":"2023-02-01","cited_by_count":1,"area":null},{"id":"2405.16739","title":"Oracle-Efficient Reinforcement Learning for Max Value Ensembles","created":"2024-05-27","cited_by_count":1,"area":"deeprl"},{"id":"2502.06261","title":"Reducing Variance Caused by Communication in Decentralized Multi-agent Deep Reinforcement Learning","created":"2025-02-10","cited_by_count":1,"area":null},{"id":"2601.00781","title":"Categorical Reparameterization with Denoising Diffusion models","created":"2026-01-02","cited_by_count":1,"area":"diffusion"},{"id":"2607.16257","title":"From Outcomes to Actions: Leveraging Hindsight for Long-Horizon Language Agent Training","created":"2026-06-28","cited_by_count":1,"area":"agents"},{"id":"2206.08499","title":"A Parametric Class of Approximate Gradient Updates for Policy Optimization","created":"2022-06-17","cited_by_count":0,"area":null},{"id":"2210.07312","title":"Bootstrap Advantage Estimation for Policy Optimization in Reinforcement Learning","created":"2022-10-13","cited_by_count":0,"area":null},{"id":"2301.12174","title":"Stochastic Dimension-reduced Second-order Methods for Policy Optimization","created":"2023-01-28","cited_by_count":0,"area":null},{"id":"2306.01789","title":"Edit Distance based RL for RNNT decoding","created":"2023-05-31","cited_by_count":0,"area":null},{"id":"2404.11834","title":"Actor-Critic Reinforcement Learning with Phased Actor","created":"2024-04-18","cited_by_count":0,"area":"deeprl"},{"id":"2405.02572","title":"Off-OAB: Off-Policy Policy Gradient Method with Optimal Action-Dependent Baseline","created":"2024-05-04","cited_by_count":0,"area":"deeprl"},{"id":"2601.21523","title":"Explicit Credit Assignment through Local Rewards and Dependence Graphs in Multi-Agent Reinforcement Learning","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2604.17744","title":"Input-Side Variance Suppression under Non-Normal Transient Amplification in Continuous-Control Reinforcement Learning","created":"2026-04-20","cited_by_count":0,"area":"deeprl"},{"id":"2604.22785","title":"Marginal-Contribution Policy Gradients under Filtered Feedback for Multi-Agent LLMs","created":"2026-04-03","cited_by_count":0,"area":"agents"},{"id":"2607.16177","title":"Physics-enhanced reinforcement learning for real-time optimal control of dynamical systems","created":"2026-07-17","cited_by_count":0,"area":"deeprl"},{"id":"2608.02073","title":"Accelerating Evolutionary Strategy via Rao-Blackwellizing Realization of Uncertain Input","created":"2026-08-03","cited_by_count":0,"area":null},{"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":"2608.29256","title":"Sense Once, Serve Many: Common-Trace Factorized Constrained PPO for Online Sensing-Session Consolidation in Multi-Tenant ISAC Networks","created":"2026-08-29","cited_by_count":0,"area":"deeprl"},{"id":"2610.04766","title":"Variance-Optimal Control Variates for Learning with Black-box Feedback","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.14942","title":"Probabilistic Multi-Source Data Selection via Learnable Categorical Priors: Variance Reduction and Guaranteed Derandomization","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}