{"total":173,"rows":[{"id":"2503.20783","title":"Understanding R1-Zero-Like Training: A Critical Perspective","created":"2025-03-26","cited_by_count":1345,"area":"lr"},{"id":"2505.22617","title":"The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models","created":"2025-05-28","cited_by_count":485,"area":"lr"},{"id":"2506.14758","title":"Reasoning with Exploration: An Entropy Perspective","created":"2025-06-17","cited_by_count":281,"area":"lr"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"1806.05635","title":"Self-Imitation Learning","created":"2018-06-14","cited_by_count":138,"area":"offlinerl"},{"id":"2106.10783","title":"OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation","created":"2021-06-21","cited_by_count":121,"area":"offlinerl"},{"id":"2305.13122","title":"Policy Representation via Diffusion Probability Model for Reinforcement Learning","created":"2023-05-22","cited_by_count":112,"area":"diffusion"},{"id":"2504.03380","title":"Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning","created":"2025-04-04","cited_by_count":104,"area":"lr"},{"id":"2111.11232","title":"Policy Gradient and Actor-Critic Learning in Continuous Time and Space: Theory and Algorithms","created":"2021-11-22","cited_by_count":101,"area":null},{"id":"2407.13734","title":"Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review","created":"2024-07-18","cited_by_count":98,"area":"diffusion"},{"id":"2504.05520","title":"Efficient Reinforcement Finetuning via Adaptive Curriculum Learning","created":"2025-04-07","cited_by_count":93,"area":"lr"},{"id":"2207.00713","title":"q-Learning in Continuous Time","created":"2022-07-02","cited_by_count":91,"area":null},{"id":"2407.16677","title":"From Imitation to Refinement -- Residual RL for Precise Assembly","created":"2024-07-23","cited_by_count":90,"area":null},{"id":"2402.19464","title":"Curiosity-driven Red-teaming for Large Language Models","created":"2024-02-29","cited_by_count":88,"area":"safety"},{"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":"2112.11701","title":"Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination","created":"2021-12-22","cited_by_count":70,"area":null},{"id":"2310.12934","title":"Generative Flow Networks as Entropy-Regularized RL","created":"2023-10-19","cited_by_count":64,"area":null},{"id":"2304.07297","title":"Language Instructed Reinforcement Learning for Human-AI Coordination","created":"2023-04-13","cited_by_count":63,"area":null},{"id":"2405.18540","title":"Learning diverse attacks on large language models for robust red-teaming and safety tuning","created":"2024-05-28","cited_by_count":54,"area":"safety"},{"id":"2210.03308","title":"Generative Augmented Flow Networks","created":"2022-10-07","cited_by_count":50,"area":null},{"id":"2505.17667","title":"QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning","created":"2025-05-23","cited_by_count":50,"area":"lr"},{"id":"2405.19107","title":"Offline Regularised Reinforcement Learning for Large Language Models Alignment","created":"2024-05-29","cited_by_count":48,"area":"alignment"},{"id":"2402.10309","title":"Discrete Probabilistic Inference as Control in Multi-path Environments","created":"2024-02-15","cited_by_count":44,"area":null},{"id":"2107.08285","title":"Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences","created":"2021-07-17","cited_by_count":41,"area":null},{"id":"2106.07704","title":"Efficient (Soft) Q-Learning for Text Generation with Limited Good Data","created":"2021-06-14","cited_by_count":37,"area":null},{"id":"2106.06613","title":"A New Formalism, Method and Open Issues for Zero-Shot Coordination","created":"2021-06-11","cited_by_count":33,"area":null},{"id":"2303.08059","title":"Fast Rates for Maximum Entropy Exploration","created":"2023-03-14","cited_by_count":33,"area":null},{"id":"2411.04625","title":"Sharp Analysis for KL-Regularized Contextual Bandits and RLHF","created":"2024-11-07","cited_by_count":33,"area":"alignment"},{"id":"2101.07012","title":"Regularized Policies are Reward Robust","created":"2021-01-18","cited_by_count":32,"area":null},{"id":"2301.13589","title":"Policy Gradient for Rectangular Robust Markov Decision Processes","created":"2023-01-31","cited_by_count":31,"area":null},{"id":"2506.09477","title":"On a few pitfalls in KL divergence gradient estimation for RL","created":"2025-06-11","cited_by_count":29,"area":null},{"id":"2509.23863","title":"SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language Models","created":"2025-09-28","cited_by_count":29,"area":"lr"},{"id":"2106.10517","title":"A Max-Min Entropy Framework for Reinforcement Learning","created":"2021-06-19","cited_by_count":28,"area":null},{"id":"2505.15692","title":"TemplateRL: Structured Template-Guided Reinforcement Learning for LLM Reasoning","created":"2025-05-21","cited_by_count":28,"area":"lr"},{"id":"2110.10719","title":"Estimating Optimal Infinite Horizon Dynamic Treatment Regimes via pT-Learning","created":"2021-10-20","cited_by_count":26,"area":null},{"id":"2110.10117","title":"Beyond Exact Gradients: Convergence of Stochastic Soft-Max Policy Gradient Methods with Entropy Regularization","created":"2021-10-19","cited_by_count":25,"area":null},{"id":"2010.08920","title":"Average-reward model-free reinforcement learning: a systematic review and literature mapping","created":"2020-10-18","cited_by_count":22,"area":"alignment"},{"id":"2205.14590","title":"Independent and Decentralized Learning in Markov Potential Games","created":"2022-05-29","cited_by_count":22,"area":null},{"id":"2306.16208","title":"Continuous-time q-learning for mean-field control problems","created":"2023-06-28","cited_by_count":22,"area":null},{"id":"2102.11866","title":"Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality","created":"2021-02-23","cited_by_count":21,"area":null},{"id":"2205.14327","title":"Efficient Policy Iteration for Robust Markov Decision Processes via Regularization","created":"2022-05-28","cited_by_count":20,"area":null},{"id":"2310.06147","title":"Reinforcement Learning in the Era of LLMs: What is Essential? What is needed? An RL Perspective on RLHF, Prompting, and Beyond","created":"2023-10-09","cited_by_count":20,"area":"alignment"},{"id":"2212.13936","title":"On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations","created":"2022-12-28","cited_by_count":19,"area":null},{"id":"2402.08733","title":"Experts Don't Cheat: Learning What You Don't Know By Predicting Pairs","created":"2024-02-13","cited_by_count":19,"area":null},{"id":"2505.16826","title":"KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical Reasoning","created":"2025-05-22","cited_by_count":19,"area":"lr"},{"id":"2101.00240","title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications","created":"2021-01-01","cited_by_count":17,"area":null},{"id":"2510.08457","title":"ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping","created":"2025-10-09","cited_by_count":17,"area":"lr"},{"id":"2206.00059","title":"A Mixture-of-Expert Approach to RL-based Dialogue Management","created":"2022-05-31","cited_by_count":16,"area":"moe"},{"id":"2402.14528","title":"ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization","created":"2024-02-22","cited_by_count":16,"area":"deeprl"},{"id":"2405.15821","title":"Reinforcing Language Agents via Policy Optimization with Action Decomposition","created":"2024-05-23","cited_by_count":16,"area":"agents"},{"id":"2303.01049","title":"Model-based Constrained MDP for Budget Allocation in Sequential Incentive Marketing","created":"2023-03-02","cited_by_count":15,"area":null},{"id":"2506.01320","title":"Psi-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models","created":"2025-06-02","cited_by_count":15,"area":"diffusion"},{"id":"2504.02367","title":"Reinforcement Fine-Tuning for Materials Design","created":"2025-04-03","cited_by_count":13,"area":null},{"id":"2103.02886","title":"Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings","created":"2021-03-04","cited_by_count":12,"area":null},{"id":"2206.03192","title":"Generalized Data Distribution Iteration","created":"2022-06-07","cited_by_count":12,"area":null},{"id":"2210.00750","title":"Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient","created":"2022-10-03","cited_by_count":12,"area":"offlinerl"},{"id":"2210.03209","title":"Self-Adaptive Driving in Nonstationary Environments through Conjectural Online Lookahead Adaptation","created":"2022-10-06","cited_by_count":12,"area":"driving"},{"id":"2402.06700","title":"Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement","created":"2024-02-09","cited_by_count":12,"area":"agents"},{"id":"2503.05453","title":"Soft Policy Optimization: Online Off-Policy RL for Sequence Models","created":"2025-03-07","cited_by_count":12,"area":null},{"id":"2510.08141","title":"SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training","created":"2025-10-09","cited_by_count":12,"area":"lr"},{"id":"2505.14975","title":"Flattening Hierarchies with Policy Bootstrapping","created":"2025-05-20","cited_by_count":11,"area":"synth"},{"id":"2505.15311","title":"Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning","created":"2025-05-21","cited_by_count":11,"area":"lr"},{"id":"2507.01551","title":"Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning","created":"2025-07-02","cited_by_count":11,"area":"lr"},{"id":"2509.22601","title":"Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning","created":"2025-09-26","cited_by_count":11,"area":"agents"},{"id":"2603.19685","title":"A Subgoal-driven Framework for Improving Long-Horizon LLM Agents","created":"2026-03-20","cited_by_count":11,"area":"agents"},{"id":"2302.02392","title":"Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage","created":"2023-02-05","cited_by_count":10,"area":"offlinerl"},{"id":"2106.06932","title":"Characterizing the Gap Between Actor-Critic and Policy Gradient","created":"2021-06-13","cited_by_count":9,"area":null},{"id":"2306.09995","title":"Fairness in Preference-based Reinforcement Learning","created":"2023-06-16","cited_by_count":9,"area":null},{"id":"2310.06253","title":"A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning","created":"2023-10-10","cited_by_count":9,"area":null},{"id":"2404.12598","title":"Continuous-time Risk-sensitive Reinforcement Learning via Quadratic Variation Penalty","created":"2024-04-19","cited_by_count":9,"area":"deeprl"},{"id":"2512.07478","title":"Enhancing Agentic RL with Progressive Reward Shaping and Value-based Sampling Policy Optimization","created":"2025-12-08","cited_by_count":9,"area":"lr"},{"id":"2105.00990","title":"Hierarchical Reinforcement Learning for Air Combat at DARPA's AlphaDogfight Trials","created":"2021-05-03","cited_by_count":8,"area":null},{"id":"2109.11767","title":"Improved Soft Actor-Critic: Mixing Prioritized Off-Policy Samples with On-Policy Experience","created":"2021-09-24","cited_by_count":8,"area":null},{"id":"2111.02994","title":"Towards an Understanding of Default Policies in Multitask Policy Optimization","created":"2021-11-04","cited_by_count":8,"area":null},{"id":"2208.02294","title":"Dynamic Planning in Open-Ended Dialogue using Reinforcement Learning","created":"2022-07-25","cited_by_count":8,"area":null},{"id":"2406.13655","title":"Improving GFlowNets with Monte Carlo Tree Search","created":"2024-06-19","cited_by_count":8,"area":null},{"id":"2512.15605","title":"Autoregressive Language Models are Secretly Energy-Based Models: Insights into the Lookahead Capabilities of Next-Token Prediction","created":"2025-12-17","cited_by_count":8,"area":null},{"id":"2007.07812","title":"Inverse Reinforcement Learning from a Gradient-based Learner","created":"2020-07-15","cited_by_count":7,"area":"offlinerl"},{"id":"2102.03261","title":"Revisiting Prioritized Experience Replay: A Value Perspective","created":"2021-02-05","cited_by_count":7,"area":null},{"id":"2106.00707","title":"An Entropy Regularization Free Mechanism for Policy-based Reinforcement Learning","created":"2021-06-01","cited_by_count":7,"area":null},{"id":"2106.06232","title":"GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning","created":"2021-06-11","cited_by_count":7,"area":null},{"id":"2109.06362","title":"Theoretical Guarantees of Fictitious Discount Algorithms for Episodic Reinforcement Learning and Global Convergence of Policy Gradient Methods","created":"2021-09-13","cited_by_count":7,"area":null},{"id":"2205.10316","title":"Complex behavior from intrinsic motivation to occupy action-state path space","created":"2022-05-20","cited_by_count":7,"area":null},{"id":"2406.01423","title":"Value Improved Actor Critic Algorithms","created":"2024-06-03","cited_by_count":7,"area":"deeprl"},{"id":"2502.01692","title":"Fast Direct: Query-Efficient Online Black-box Guidance for Diffusion-model Target Generation","created":"2025-02-02","cited_by_count":7,"area":"diffusion"},{"id":"2604.17415","title":"Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models","created":"2026-04-19","cited_by_count":7,"area":"diffusion"},{"id":"2201.12434","title":"Do You Need the Entropy Reward (in Practice)?","created":"2022-01-28","cited_by_count":6,"area":null},{"id":"2202.07071","title":"A Unified Perspective on Value Backup and Exploration in Monte-Carlo Tree Search","created":"2022-02-11","cited_by_count":6,"area":null},{"id":"2301.13642","title":"An Efficient Solution to s-Rectangular Robust Markov Decision Processes","created":"2023-01-31","cited_by_count":6,"area":null},{"id":"2502.13723","title":"Direct Value Optimization: Improving Chain-of-Thought Reasoning in LLMs with Refined Values","created":"2025-02-19","cited_by_count":6,"area":"lr"},{"id":"2601.22582","title":"MC-GRPO: Median-Centered Group Relative Policy Optimization for Small-Rollout Reinforcement Learning","created":"2026-01-30","cited_by_count":6,"area":"lr"},{"id":"2110.12359","title":"Self-learned Intelligence for Integrated Decision and Control of Automated Vehicles at Signalized Intersections","created":"2021-10-24","cited_by_count":5,"area":null},{"id":"2206.03139","title":"Intra-agent speech permits zero-shot task acquisition","created":"2022-06-07","cited_by_count":5,"area":null},{"id":"2402.07963","title":"SPO: Sequential Monte Carlo Policy Optimisation","created":"2024-02-12","cited_by_count":5,"area":null},{"id":"2406.02213","title":"Random Policy Evaluation Uncovers Policies of Generative Flow Networks","created":"2024-06-04","cited_by_count":5,"area":null},{"id":"2408.05885","title":"GFlowNet Training by Policy Gradients","created":"2024-08-12","cited_by_count":5,"area":"deeprl"},{"id":"2512.04559","title":"Diffusion Fine-Tuning via Reparameterized Policy Gradient of the Soft Q-Function","created":"2025-12-04","cited_by_count":5,"area":"diffusion"},{"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":"2602.04417","title":"EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL","created":"2026-02-04","cited_by_count":5,"area":"lr"},{"id":"2112.15364","title":"Robust Entropy-regularized Markov Decision Processes","created":"2021-12-31","cited_by_count":4,"area":"offlinerl"}],"next_cursor":"100"}