{"total":286,"rows":[{"id":"2310.12036","title":"A General Theoretical Paradigm to Understand Learning from Human Preferences","created":"2023-10-18","cited_by_count":912,"area":"alignment"},{"id":"2309.00267","title":"RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback","created":"2023-09-01","cited_by_count":625,"area":"alignment"},{"id":"2106.06926","title":"Bellman-consistent Pessimism for Offline Reinforcement Learning","created":"2021-06-13","cited_by_count":269,"area":"offlinerl"},{"id":"2312.00886","title":"Nash Learning from Human Feedback","created":"2023-12-01","cited_by_count":224,"area":"alignment"},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176,"area":null},{"id":"2401.12187","title":"WARM: On the Benefits of Weight Averaged Reward Models","created":"2024-01-22","cited_by_count":147,"area":"alignment"},{"id":"2408.08252","title":"Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding","created":"2024-08-15","cited_by_count":136,"area":"diffusion"},{"id":"2303.15810","title":"Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization","created":"2023-03-28","cited_by_count":116,"area":"offlinerl"},{"id":"2202.02446","title":"Adversarially Trained Actor Critic for Offline Reinforcement Learning","created":"2022-02-05","cited_by_count":111,"area":"offlinerl"},{"id":"2108.08812","title":"Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning","created":"2021-08-19","cited_by_count":110,"area":"offlinerl"},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"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":"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":"2007.08202","title":"Provably Good Batch Reinforcement Learning Without Great Exploration","created":"2020-07-16","cited_by_count":77,"area":"offlinerl"},{"id":"2407.14622","title":"BOND: Aligning LLMs with Best-of-N Distillation","created":"2024-07-19","cited_by_count":76,"area":"alignment"},{"id":"2109.00157","title":"A Survey of Exploration Methods in Reinforcement Learning","created":"2021-09-01","cited_by_count":73,"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":"2405.14655","title":"Multi-turn Reinforcement Learning from Preference Human Feedback","created":"2024-05-23","cited_by_count":67,"area":"alignment"},{"id":"2310.12934","title":"Generative Flow Networks as Entropy-Regularized RL","created":"2023-10-19","cited_by_count":64,"area":null},{"id":"2105.15186","title":"Fast Policy Extragradient Methods for Competitive Games with Entropy Regularization","created":"2021-05-31","cited_by_count":63,"area":null},{"id":"2106.03787","title":"Concave Utility Reinforcement Learning: the Mean-Field Game Viewpoint","created":"2021-06-07","cited_by_count":56,"area":null},{"id":"2103.12923","title":"Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation","created":"2021-03-24","cited_by_count":53,"area":null},{"id":"2402.16359","title":"Feedback Efficient Online Fine-Tuning of Diffusion Models","created":"2024-02-26","cited_by_count":53,"area":"diffusion"},{"id":"2105.01424","title":"On the Linear convergence of Natural Policy Gradient Algorithm","created":"2021-05-04","cited_by_count":48,"area":null},{"id":"2102.04376","title":"Adversarially Guided Actor-Critic","created":"2021-02-08","cited_by_count":47,"area":null},{"id":"2110.06267","title":"Twice regularized MDPs and the equivalence between robustness and regularization","created":"2021-10-12","cited_by_count":47,"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":"2406.16768","title":"WARP: On the Benefits of Weight Averaged Rewarded Policies","created":"2024-06-24","cited_by_count":45,"area":"alignment"},{"id":"2106.06431","title":"Offline Reinforcement Learning as Anti-Exploration","created":"2021-06-11","cited_by_count":44,"area":"offlinerl"},{"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":"2203.06662","title":"DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning","created":"2022-03-13","cited_by_count":41,"area":"offlinerl"},{"id":"2106.10268","title":"MADE: Exploration via Maximizing Deviation from Explored Regions","created":"2021-06-18","cited_by_count":40,"area":null},{"id":"2101.10506","title":"Finite Sample Analysis of Two-Time-Scale Natural Actor-Critic Algorithm","created":"2021-01-26","cited_by_count":39,"area":null},{"id":"2502.12668","title":"Evaluation of Best-of-N Sampling Strategies for Language Model Alignment","created":"2025-02-18","cited_by_count":39,"area":"alignment"},{"id":"2110.09796","title":"Offline Reinforcement Learning with Value-based Episodic Memory","created":"2021-10-19","cited_by_count":36,"area":"offlinerl"},{"id":"2209.09203","title":"Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement Learning","created":"2022-09-16","cited_by_count":34,"area":null},{"id":"2506.23235","title":"Generalist Reward Models: Found Inside Large Language Models","created":"2025-06-29","cited_by_count":34,"area":"alignment"},{"id":"2007.01174","title":"Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch","created":"2020-07-02","cited_by_count":33,"area":"offlinerl"},{"id":"2411.04625","title":"Sharp Analysis for KL-Regularized Contextual Bandits and RLHF","created":"2024-11-07","cited_by_count":33,"area":"alignment"},{"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":"2312.14331","title":"Maximum entropy GFlowNets with soft Q-learning","created":"2023-12-21","cited_by_count":30,"area":null},{"id":"2102.06924","title":"Online Apprenticeship Learning","created":"2021-02-13","cited_by_count":29,"area":null},{"id":"2306.12755","title":"Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learning","created":"2023-06-22","cited_by_count":27,"area":"offlinerl"},{"id":"2102.09318","title":"Finite-Sample Analysis of Off-Policy Natural Actor-Critic Algorithm","created":"2021-02-18","cited_by_count":26,"area":null},{"id":"2209.10968","title":"Proximal Point Imitation Learning","created":"2022-09-22","cited_by_count":26,"area":"offlinerl"},{"id":"2210.01050","title":"Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games","created":"2022-10-03","cited_by_count":26,"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":"2211.00617","title":"Convergence of policy gradient methods for finite-horizon exploratory linear-quadratic control problems","created":"2022-11-01","cited_by_count":25,"area":null},{"id":"2405.19673","title":"Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models","created":"2024-05-30","cited_by_count":25,"area":"diffusion"},{"id":"2206.03378","title":"Imitating Past Successes can be Very Suboptimal","created":"2022-06-07","cited_by_count":23,"area":"offlinerl"},{"id":"2211.16715","title":"Policy Optimization over General State and Action Spaces","created":"2022-11-30","cited_by_count":23,"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":"2105.12540","title":"Finite-Sample Analysis of Off-Policy Natural Actor-Critic with Linear Function Approximation","created":"2021-05-26","cited_by_count":22,"area":null},{"id":"2210.06692","title":"Model-Based Offline Reinforcement Learning with Pessimism-Modulated Dynamics Belief","created":"2022-10-13","cited_by_count":22,"area":"offlinerl"},{"id":"2302.05372","title":"Towards Minimax Optimality of Model-based Robust Reinforcement Learning","created":"2023-02-10","cited_by_count":22,"area":null},{"id":"2305.16498","title":"Coherent Soft Imitation Learning","created":"2023-05-25","cited_by_count":22,"area":"offlinerl"},{"id":"2410.18640","title":"Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model","created":"2024-10-24","cited_by_count":22,"area":"alignment"},{"id":"2201.07296","title":"Convergence of Policy Gradient for Entropy Regularized MDPs with Neural Network Approximation in the Mean-Field Regime","created":"2022-01-18","cited_by_count":21,"area":null},{"id":"2203.12592","title":"Your Policy Regularizer is Secretly an Adversary","created":"2022-03-23","cited_by_count":21,"area":null},{"id":"2206.09495","title":"The Power of Regularization in Solving Extensive-Form Games","created":"2022-06-19","cited_by_count":21,"area":null},{"id":"2409.01369","title":"Imitating Language via Scalable Inverse Reinforcement Learning","created":"2024-09-02","cited_by_count":21,"area":"offlinerl"},{"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":"2302.07690","title":"Online Statistical Inference for Nonlinear Stochastic Approximation with Markovian Data","created":"2023-02-15","cited_by_count":20,"area":null},{"id":"2202.00079","title":"You May Not Need Ratio Clipping in PPO","created":"2022-01-31","cited_by_count":19,"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":"2302.11381","title":"Optimal Convergence Rate for Exact Policy Mirror Descent in Discounted Markov Decision Processes","created":"2023-02-22","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":"2106.04096","title":"Linear Convergence of Entropy-Regularized Natural Policy Gradient with Linear Function Approximation","created":"2021-06-08","cited_by_count":16,"area":null},{"id":"2202.05404","title":"Regularized Q-learning","created":"2022-02-11","cited_by_count":16,"area":null},{"id":"2209.10974","title":"Identifiability and generalizability from multiple experts in Inverse Reinforcement Learning","created":"2022-09-22","cited_by_count":16,"area":"offlinerl"},{"id":"2306.00629","title":"Identifiability and Generalizability in Constrained Inverse Reinforcement Learning","created":"2023-06-01","cited_by_count":16,"area":"offlinerl"},{"id":"2406.04274","title":"Self-Play with Adversarial Critic: Provable and Scalable Offline Alignment for Language Models","created":"2024-06-06","cited_by_count":16,"area":"alignment"},{"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":"2105.04321","title":"Reinforcement learning of rare diffusive dynamics","created":"2021-05-10","cited_by_count":15,"area":null},{"id":"2406.15788","title":"Distributionally Robust Constrained Reinforcement Learning under Strong Duality","created":"2024-06-22","cited_by_count":15,"area":"deeprl"},{"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":"2106.05068","title":"Offline Inverse Reinforcement Learning","created":"2021-06-09","cited_by_count":14,"area":"offlinerl"},{"id":"2410.15474","title":"Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization","created":"2024-10-20","cited_by_count":14,"area":null},{"id":"2103.11559","title":"Provably Correct Optimization and Exploration with Non-linear Policies","created":"2021-03-22","cited_by_count":13,"area":null},{"id":"2110.11280","title":"Actor-critic is implicitly biased towards high entropy optimal policies","created":"2021-10-21","cited_by_count":13,"area":null},{"id":"2205.14211","title":"KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal","created":"2022-05-27","cited_by_count":13,"area":null},{"id":"2406.19185","title":"Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion","created":"2024-06-27","cited_by_count":13,"area":"alignment"},{"id":"2405.16601","title":"A CMDP-within-online framework for Meta-Safe Reinforcement Learning","created":"2024-05-26","cited_by_count":12,"area":"deeprl"},{"id":"2108.08765","title":"Provably Efficient Generative Adversarial Imitation Learning for Online and Offline Setting with Linear Function Approximation","created":"2021-08-19","cited_by_count":11,"area":"offlinerl"},{"id":"2311.13294","title":"Probabilistic Inference in Reinforcement Learning Done Right","created":"2023-11-22","cited_by_count":11,"area":null},{"id":"2505.12504","title":"CPGD: Toward Stable Rule-based Reinforcement Learning for Language Models","created":"2025-05-18","cited_by_count":11,"area":"lr"},{"id":"2509.22611","title":"Quantile Advantage Estimation: Stabilizing RLVR for LLM Reasoning","created":"2025-09-26","cited_by_count":11,"area":"lr"},{"id":"2206.06841","title":"Robust Reinforcement Learning with Distributional Risk-averse formulation","created":"2022-06-14","cited_by_count":10,"area":null},{"id":"2209.10187","title":"On the convex formulations of robust Markov decision processes","created":"2022-09-21","cited_by_count":10,"area":null},{"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":"2306.05726","title":"Iteratively Refined Behavior Regularization for Offline Reinforcement Learning","created":"2023-06-09","cited_by_count":10,"area":"offlinerl"},{"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":"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":"2502.06051","title":"Towards a Sharp Analysis of Offline Policy Learning for $f$-Divergence-Regularized Contextual Bandits","created":"2025-02-09","cited_by_count":10,"area":"offlinerl"},{"id":"2502.07735","title":"Revisiting Non-Acyclic GFlowNets in Discrete Environments","created":"2025-02-11","cited_by_count":10,"area":null},{"id":"2512.16626","title":"Stackelberg Learning from Human Feedback: Preference Optimization as a Sequential Game","created":"2025-12-18","cited_by_count":10,"area":"alignment"},{"id":"2010.03691","title":"Regularized Inverse Reinforcement Learning","created":"2020-10-07","cited_by_count":9,"area":"offlinerl"},{"id":"2108.07041","title":"Implicitly Regularized RL with Implicit Q-Values","created":"2021-08-16","cited_by_count":9,"area":null}],"next_cursor":"100"}