{"total":106,"rows":[{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210,"area":"lr"},{"id":"2503.16419","title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","created":"2025-03-20","cited_by_count":464,"area":"lr"},{"id":"2505.24864","title":"ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models","created":"2025-05-30","cited_by_count":194,"area":"lr"},{"id":"2102.00135","title":"Policy Mirror Descent for Reinforcement Learning: Linear Convergence, New Sampling Complexity, and Generalized Problem Classes","created":"2021-01-30","cited_by_count":156,"area":null},{"id":"2503.06639","title":"Reinforcement Learning with Verifiable Rewards: GRPO's Effective Loss, Dynamics, and Success Amplification","created":"2025-03-09","cited_by_count":110,"area":"lr"},{"id":"2105.11066","title":"Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence","created":"2021-05-24","cited_by_count":84,"area":null},{"id":"2106.00661","title":"Reward is enough for convex MDPs","created":"2021-06-01","cited_by_count":84,"area":null},{"id":"2107.11433","title":"A general sample complexity analysis of vanilla policy gradient","created":"2021-07-23","cited_by_count":76,"area":null},{"id":"2306.00186","title":"Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2502.00361","title":"Efficient Online Reinforcement Learning for Diffusion Policy","created":"2025-02-01","cited_by_count":71,"area":"diffusion"},{"id":"2405.14655","title":"Multi-turn Reinforcement Learning from Preference Human Feedback","created":"2024-05-23","cited_by_count":67,"area":"alignment"},{"id":"2206.05825","title":"A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games","created":"2022-06-12","cited_by_count":66,"area":null},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53,"area":null},{"id":"2210.01400","title":"Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies","created":"2022-10-04","cited_by_count":46,"area":null},{"id":"2109.04504","title":"Bootstrapped Meta-Learning","created":"2021-09-09","cited_by_count":45,"area":null},{"id":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45,"area":"alignment"},{"id":"2504.21277","title":"Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models","created":"2025-04-30","cited_by_count":44,"area":"lr"},{"id":"2110.00641","title":"Batch size-invariance for policy optimization","created":"2021-10-01","cited_by_count":35,"area":null},{"id":"2201.02373","title":"Mirror Learning: A Unifying Framework of Policy Optimisation","created":"2022-01-07","cited_by_count":31,"area":null},{"id":"2301.13139","title":"A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence","created":"2023-01-30","cited_by_count":30,"area":null},{"id":"2102.06924","title":"Online Apprenticeship Learning","created":"2021-02-13","cited_by_count":29,"area":null},{"id":"2212.14449","title":"Policy Mirror Ascent for Efficient and Independent Learning in Mean Field Games","created":"2022-12-29","cited_by_count":26,"area":null},{"id":"2310.02951","title":"A Fisher-Rao gradient flow for entropy-regularised Markov decision processes in Polish spaces","created":"2023-10-04","cited_by_count":23,"area":null},{"id":"2507.23675","title":"One-Step Flow Policy Mirror Descent","created":"2025-07-31","cited_by_count":21,"area":"diffusion"},{"id":"2302.01275","title":"ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs","created":"2023-02-02","cited_by_count":20,"area":null},{"id":"2410.16714","title":"Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model Alignment","created":"2024-10-22","cited_by_count":20,"area":"alignment"},{"id":"2202.00079","title":"You May Not Need Ratio Clipping in PPO","created":"2022-01-31","cited_by_count":19,"area":null},{"id":"2102.12611","title":"Improved Regret Bound and Experience Replay in Regularized Policy Iteration","created":"2021-02-25","cited_by_count":18,"area":null},{"id":"2108.05828","title":"A general class of surrogate functions for stable and efficient reinforcement learning","created":"2021-08-12","cited_by_count":18,"area":null},{"id":"2106.12112","title":"Bregman Gradient Policy Optimization","created":"2021-06-23","cited_by_count":17,"area":null},{"id":"2308.12372","title":"Vision Transformer Adapters for Generalizable Multitask Learning","created":"2023-08-23","cited_by_count":14,"area":null},{"id":"2106.08414","title":"On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control","created":"2021-06-15","cited_by_count":12,"area":null},{"id":"2205.10047","title":"The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measure","created":"2022-05-20","cited_by_count":12,"area":null},{"id":"2405.20250","title":"Entropy annealing for policy mirror descent in continuous time and space","created":"2024-05-30","cited_by_count":12,"area":null},{"id":"2606.29502","title":"UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation","created":"2026-06-28","cited_by_count":12,"area":"agents"},{"id":"2201.12332","title":"On the Hidden Biases of Policy Mirror Ascent in Continuous Action Spaces","created":"2022-01-28","cited_by_count":11,"area":null},{"id":"2102.06234","title":"Optimization Issues in KL-Constrained Approximate Policy Iteration","created":"2021-02-11","cited_by_count":10,"area":null},{"id":"2411.02957","title":"Embedding Safety into RL: A New Take on Trust Region Methods","created":"2024-11-05","cited_by_count":10,"area":"deeprl"},{"id":"2602.13953","title":"QuRL: Efficient Reinforcement Learning with Quantized Rollout","created":"2026-02-15","cited_by_count":8,"area":"lr"},{"id":"2112.05848","title":"Faster Deep Reinforcement Learning with Slower Online Network","created":"2021-12-10","cited_by_count":7,"area":null},{"id":"2507.11019","title":"Relative Entropy Pathwise Policy Optimization","created":"2025-07-15","cited_by_count":7,"area":"deeprl"},{"id":"2509.22963","title":"Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces","created":"2025-09-26","cited_by_count":7,"area":"diffusion"},{"id":"2210.11201","title":"Robust Imitation via Mirror Descent Inverse Reinforcement Learning","created":"2022-10-20","cited_by_count":6,"area":"offlinerl"},{"id":"2401.01084","title":"Global Convergence of Natural Policy Gradient with Hessian-aided Momentum Variance Reduction","created":"2024-01-02","cited_by_count":6,"area":"deeprl"},{"id":"2403.14156","title":"Policy Mirror Descent with Lookahead","created":"2024-03-21","cited_by_count":6,"area":"deeprl"},{"id":"2511.21750","title":"SO-Bench: A Structural Output Evaluation of Multimodal LLMs","created":"2025-11-23","cited_by_count":6,"area":"mllm"},{"id":"2102.10616","title":"Dealing with Non-Stationarity in MARL via Trust-Region Decomposition","created":"2021-02-21","cited_by_count":5,"area":null},{"id":"2503.00030","title":"RSPO: Regularized Self-Play Alignment of Large Language Models","created":"2025-02-24","cited_by_count":5,"area":"alignment"},{"id":"2606.09821","title":"Rethinking the Divergence Regularization in LLM RL","created":"2026-06-08","cited_by_count":5,"area":"lr"},{"id":"2204.09315","title":"Learning to Constrain Policy Optimization with Virtual Trust Region","created":"2022-04-20","cited_by_count":4,"area":null},{"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":"2601.18175","title":"Success Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success","created":"2026-01-26","cited_by_count":4,"area":null},{"id":"2605.14967","title":"InfoSFT: Learn More and Forget Less with Information-Aware Token Weighting","created":"2026-05-14","cited_by_count":4,"area":null},{"id":"2605.25507","title":"Credit Assignment with Resets in Language Model Reasoning","created":"2026-05-25","cited_by_count":4,"area":"lr"},{"id":"2110.02398","title":"Approximate Newton policy gradient algorithms","created":"2021-10-05","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":"2305.15249","title":"Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2407.16602","title":"Functional Acceleration for Policy Mirror Descent","created":"2024-07-23","cited_by_count":3,"area":"deeprl"},{"id":"2505.15418","title":"Guided Policy Optimization under Partial Observability","created":"2025-05-21","cited_by_count":3,"area":"deeprl"},{"id":"2509.18822","title":"On the Convergence of Policy Mirror Descent with Temporal Difference Evaluation","created":"2025-09-23","cited_by_count":3,"area":"deeprl"},{"id":"2601.22801","title":"Clipping-Free Policy Optimization for Large Language Models","created":"2026-01-30","cited_by_count":3,"area":"alignment"},{"id":"2602.04620","title":"QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning","created":"2026-02-04","cited_by_count":3,"area":"lr"},{"id":"2605.06139","title":"Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex","created":"2026-05-07","cited_by_count":3,"area":"lr"},{"id":"2605.30749","title":"FLAG: Flow Policy MaxEnt-RL by Latent Augmented Guidance","created":"2026-05-29","cited_by_count":3,"area":"deeprl"},{"id":"2207.04581","title":"How Robust is your Fair Model? Exploring the Robustness of Diverse Fairness Strategies","created":"2022-07-11","cited_by_count":2,"area":null},{"id":"2405.16668","title":"Provably Efficient Off-Policy Adversarial Imitation Learning with Convergence Guarantees","created":"2024-05-26","cited_by_count":2,"area":"offlinerl"},{"id":"2410.01249","title":"Dual Approximation Policy Optimization","created":"2024-10-02","cited_by_count":2,"area":null},{"id":"2411.12042","title":"Fast Convergence of Softmax Policy Mirror Ascent","created":"2024-11-18","cited_by_count":2,"area":"deeprl"},{"id":"2502.11033","title":"Convergence of Policy Mirror Descent Beyond Compatible Function Approximation","created":"2025-02-16","cited_by_count":2,"area":null},{"id":"2601.06133","title":"A Review of Online Diffusion Policy RL Algorithms for Scalable Robotic Control","created":"2026-01-05","cited_by_count":2,"area":"diffusion"},{"id":"2603.17685","title":"Flow Matching Policy Optimization with Mirror Descent and Entropy Constraints","created":"2026-03-18","cited_by_count":2,"area":"diffusion"},{"id":"2309.13915","title":"Sample Complexity of Neural Policy Mirror Descent for Policy Optimization on Low-Dimensional Manifolds","created":"2023-09-25","cited_by_count":1,"area":null},{"id":"2310.20380","title":"Dropout Strategy in Reinforcement Learning: Limiting the Surrogate Objective Variance in Policy Optimization Methods","created":"2023-10-31","cited_by_count":1,"area":null},{"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":"2402.05187","title":"Learning mirror maps in policy mirror descent","created":"2024-02-07","cited_by_count":1,"area":"deeprl"},{"id":"2405.11746","title":"Configurable Mirror Descent: Towards a Unification of Decision Making","created":"2024-05-20","cited_by_count":1,"area":null},{"id":"2502.03854","title":"Mirror Descent Actor Critic via Bounded Advantage Learning","created":"2025-02-06","cited_by_count":1,"area":"deeprl"},{"id":"2505.12951","title":"DGRO: Enhancing LLM Reasoning via Exploration-Exploitation Control and Reward Variance Management","created":"2025-05-19","cited_by_count":1,"area":"lr"},{"id":"2507.04406","title":"Convergence and Sample Complexity of First-Order Methods for Agnostic Reinforcement Learning","created":"2025-07-06","cited_by_count":1,"area":"deeprl"},{"id":"2507.08718","title":"On the Effect of Regularization in Policy Mirror Descent","created":"2025-07-11","cited_by_count":1,"area":"deeprl"},{"id":"2509.01432","title":"The Geometry of Nonlinear Reinforcement Learning","created":"2025-09-01","cited_by_count":1,"area":"deeprl"},{"id":"2601.22211","title":"Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions","created":"2026-01-29","cited_by_count":1,"area":"deeprl"},{"id":"2603.10199","title":"Actor-Accelerated Policy Dual Averaging for Reinforcement Learning in Continuous Action Spaces","created":"2026-03-10","cited_by_count":1,"area":"deeprl"},{"id":"2603.10250","title":"GeMPO: Generalized Measure Matching for Online Diffusion Reinforcement Learning","created":"2026-03-10","cited_by_count":1,"area":"diffusion"},{"id":"2604.06159","title":"Target Policy Optimization","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2607.28560","title":"X-NavDP: Generalizing Navigation Diffusion Policy to Novel Behavior and Embodiments with Group Q-score Reweighted Matching","created":"2026-07-30","cited_by_count":1,"area":"diffusion"},{"id":"2110.12239","title":"Policy Search using Dynamic Mirror Descent MPC for Model Free Off Policy RL","created":"2021-10-23","cited_by_count":0,"area":null},{"id":"2208.09322","title":"Entropy Augmented Reinforcement Learning","created":"2022-08-19","cited_by_count":0,"area":null},{"id":"2306.10587","title":"Acceleration in Policy Optimization","created":"2023-06-18","cited_by_count":0,"area":null},{"id":"2308.06741","title":"Heterogeneous Multi-Agent Reinforcement Learning via Mirror Descent Policy Optimization","created":"2023-08-13","cited_by_count":0,"area":null},{"id":"2505.11126","title":"FedDuA: Doubly Adaptive Federated Learning","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2602.05933","title":"Approximation of Log-Partition Function in Policy Mirror Descent Induces Implicit Regularization for LLM Post-Training","created":"2026-02-05","cited_by_count":0,"area":null},{"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":"2603.21621","title":"Path-Space Mirror Descent for On-Policy Reinforcement Learning under the Generalized Schr\\\"odinger Bridge","created":"2026-03-23","cited_by_count":0,"area":"deeprl"},{"id":"2605.21282","title":"Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent","created":"2026-05-20","cited_by_count":0,"area":"deeprl"},{"id":"2607.10848","title":"Predictive Divergence Masks for LLM RL","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.10892","title":"A Single Diffusion-Policy Controller for Multi-Task Block Pushing with Zero-Shot Sim-to-Real Transfer","created":"2026-07-12","cited_by_count":0,"area":"diffusion"},{"id":"2607.13274","title":"Deconstructing Actor-Critic: A Large-scale Empirical Study of Design Components for Practitioners","created":"2026-07-14","cited_by_count":0,"area":"deeprl"},{"id":"2607.17574","title":"Predictive Training with Latent Imagination for Visual Quadruped Navigation","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2609.15987","title":"Bellman Policy Optimization","created":"2026-09-14","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}