{"total":127,"rows":[{"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":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363,"area":null},{"id":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288,"area":null},{"id":"1907.00456","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","created":"2019-06-30","cited_by_count":284,"area":"offlinerl"},{"id":"2103.08050","title":"Offline Reinforcement Learning with Fisher Divergence Critic Regularization","created":"2021-03-14","cited_by_count":238,"area":"offlinerl"},{"id":"2102.02915","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","created":"2021-02-04","cited_by_count":213,"area":null},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176,"area":null},{"id":"2105.08140","title":"Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning","created":"2021-05-17","cited_by_count":126,"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":"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":"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":"2106.13105","title":"The Option Keyboard: Combining Skills in Reinforcement Learning","created":"2021-06-24","cited_by_count":67,"area":null},{"id":"2310.12934","title":"Generative Flow Networks as Entropy-Regularized RL","created":"2023-10-19","cited_by_count":64,"area":null},{"id":"2402.10309","title":"Discrete Probabilistic Inference as Control in Multi-path Environments","created":"2024-02-15","cited_by_count":44,"area":null},{"id":"2103.12656","title":"Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification","created":"2021-03-23","cited_by_count":38,"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":"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":"2312.14331","title":"Maximum entropy GFlowNets with soft Q-learning","created":"2023-12-21","cited_by_count":30,"area":null},{"id":"2112.14582","title":"A Statistical Analysis of Polyak-Ruppert Averaged Q-learning","created":"2021-12-29","cited_by_count":29,"area":null},{"id":"2406.00633","title":"Improving GFlowNets for Text-to-Image Diffusion Alignment","created":"2024-06-02","cited_by_count":27,"area":"diffusion"},{"id":"2405.13629","title":"Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow","created":"2024-05-22","cited_by_count":26,"area":"deeprl"},{"id":"2305.16498","title":"Coherent Soft Imitation Learning","created":"2023-05-25","cited_by_count":22,"area":"offlinerl"},{"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":"2103.06224","title":"An Information-Theoretic Perspective on Credit Assignment in Reinforcement Learning","created":"2021-03-10","cited_by_count":20,"area":null},{"id":"2412.12089","title":"Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation","created":"2024-12-16","cited_by_count":20,"area":"deeprl"},{"id":"2103.00107","title":"Revisiting Peng's Q($\\lambda$) for Modern Reinforcement Learning","created":"2021-02-27","cited_by_count":19,"area":null},{"id":"2403.05996","title":"Dissecting Deep RL with High Update Ratios: Combatting Value Divergence","created":"2024-03-09","cited_by_count":17,"area":"deeprl"},{"id":"2510.11696","title":"QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2103.12726","title":"Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning","created":"2021-03-23","cited_by_count":15,"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":"2106.01404","title":"Variational Empowerment as Representation Learning for Goal-Based Reinforcement Learning","created":"2021-06-02","cited_by_count":15,"area":null},{"id":"2406.07826","title":"The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithm","created":"2024-06-12","cited_by_count":15,"area":"deeprl"},{"id":"2502.20548","title":"$Q\\sharp$: Provably Optimal Distributional RL for LLM Post-Training","created":"2025-02-27","cited_by_count":15,"area":"lr"},{"id":"2106.03155","title":"SoftDICE for Imitation Learning: Rethinking Off-policy Distribution Matching","created":"2021-06-06","cited_by_count":14,"area":"offlinerl"},{"id":"2006.07442","title":"Self-Imitation Learning via Generalized Lower Bound Q-learning","created":"2020-06-12","cited_by_count":13,"area":"offlinerl"},{"id":"2203.11409","title":"A Primer on Maximum Causal Entropy Inverse Reinforcement Learning","created":"2022-03-22","cited_by_count":13,"area":"offlinerl"},{"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":"2209.07670","title":"Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks","created":"2022-09-16","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":"2402.06700","title":"Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement","created":"2024-02-09","cited_by_count":12,"area":"agents"},{"id":"2311.13294","title":"Probabilistic Inference in Reinforcement Learning Done Right","created":"2023-11-22","cited_by_count":11,"area":null},{"id":"2408.10932","title":"The Evolution of Reinforcement Learning in Quantitative Finance: A Survey","created":"2024-08-20","cited_by_count":11,"area":"deeprl"},{"id":"2112.02852","title":"Target Entropy Annealing for Discrete Soft Actor-Critic","created":"2021-12-06","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":"2102.09677","title":"Training a Resilient Q-Network against Observational Interference","created":"2021-02-18","cited_by_count":9,"area":null},{"id":"2311.01388","title":"Time-series Generation by Contrastive Imitation","created":"2023-11-02","cited_by_count":9,"area":null},{"id":"2107.09598","title":"Learning Altruistic Behaviours in Reinforcement Learning without External Rewards","created":"2021-07-20","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":"2109.11792","title":"Regularization Guarantees Generalization in Bayesian Reinforcement Learning through Algorithmic Stability","created":"2021-09-24","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":"2302.12717","title":"Statistical Inference with Stochastic Gradient Methods under $\\phi$-mixing Data","created":"2023-02-24","cited_by_count":7,"area":null},{"id":"2305.02857","title":"Maximum Causal Entropy Inverse Constrained Reinforcement Learning","created":"2023-05-04","cited_by_count":7,"area":null},{"id":"2403.10704","title":"Parameter Efficient Reinforcement Learning from Human Feedback","created":"2024-03-15","cited_by_count":7,"area":"mllm"},{"id":"2406.01423","title":"Value Improved Actor Critic Algorithms","created":"2024-06-03","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":"2104.01040","title":"Distributional Offline Continuous-Time Reinforcement Learning with Neural Physics-Informed PDEs (SciPhy RL for DOCTR-L)","created":"2021-04-02","cited_by_count":6,"area":null},{"id":"2210.16877","title":"On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning","created":"2022-10-30","cited_by_count":6,"area":null},{"id":"2303.03955","title":"Diminishing Return of Value Expansion Methods in Model-Based Reinforcement Learning","created":"2023-03-07","cited_by_count":6,"area":null},{"id":"2306.15156","title":"Learning non-Markovian Decision-Making from State-only Sequences","created":"2023-06-27","cited_by_count":6,"area":"offlinerl"},{"id":"2603.02196","title":"Conformal Policy Control","created":"2026-03-02","cited_by_count":6,"area":null},{"id":"2405.12800","title":"Deep Reinforcement Learning for Time-Critical Wilderness Search And Rescue Using Drones","created":"2024-05-21","cited_by_count":5,"area":"deeprl"},{"id":"2406.02213","title":"Random Policy Evaluation Uncovers Policies of Generative Flow Networks","created":"2024-06-04","cited_by_count":5,"area":null},{"id":"2406.19188","title":"Averaging log-likelihoods in direct alignment","created":"2024-06-27","cited_by_count":5,"area":"alignment"},{"id":"2106.06170","title":"Taylor Expansion of Discount Factors","created":"2021-06-11","cited_by_count":4,"area":null},{"id":"2109.14419","title":"On the Estimation Bias in Double Q-Learning","created":"2021-09-29","cited_by_count":4,"area":null},{"id":"2112.15364","title":"Robust Entropy-regularized Markov Decision Processes","created":"2021-12-31","cited_by_count":4,"area":"offlinerl"},{"id":"2305.03263","title":"Bayesian Reinforcement Learning with Limited Cognitive Load","created":"2023-05-05","cited_by_count":4,"area":null},{"id":"2407.12185","title":"Satisficing Exploration for Deep Reinforcement Learning","created":"2024-07-16","cited_by_count":4,"area":"deeprl"},{"id":"2501.15034","title":"Divergence-Augmented Policy Optimization","created":"2025-01-25","cited_by_count":4,"area":"deeprl"},{"id":"2601.11217","title":"Model-free policy gradient for discrete-time mean-field control","created":"2026-01-16","cited_by_count":4,"area":"deeprl"},{"id":"2107.05217","title":"Cautious Actor-Critic","created":"2021-07-12","cited_by_count":3,"area":null},{"id":"2201.01874","title":"Combining Reinforcement Learning and Inverse Reinforcement Learning for Asset Allocation Recommendations","created":"2022-01-06","cited_by_count":3,"area":"offlinerl"},{"id":"2312.07178","title":"Beyond Expected Return: Accounting for Policy Reproducibility when Evaluating Reinforcement Learning Algorithms","created":"2023-12-12","cited_by_count":3,"area":null},{"id":"2502.12678","title":"Multi-Step Alignment as Markov Games: An Optimistic Online Gradient Descent Approach with Convergence Guarantees","created":"2025-02-18","cited_by_count":3,"area":"alignment"},{"id":"2503.21224","title":"Efficient Learning for Entropy-Regularized Markov Decision Processes via Multilevel Monte Carlo","created":"2025-03-27","cited_by_count":3,"area":null},{"id":"2602.17832","title":"MePoly: Max Entropy Polynomial Policy Optimization","created":"2026-02-19","cited_by_count":3,"area":"offlinerl"},{"id":"2103.12020","title":"Improving Actor-Critic Reinforcement Learning via Hamiltonian Monte Carlo Method","created":"2021-03-22","cited_by_count":2,"area":null},{"id":"2110.14818","title":"Temporal-Difference Value Estimation via Uncertainty-Guided Soft Updates","created":"2021-10-28","cited_by_count":2,"area":null},{"id":"2210.17272","title":"Reinforcement Learning-based Defect Mitigation for Quality Assurance of Additive Manufacturing","created":"2022-10-28","cited_by_count":2,"area":null},{"id":"2405.08691","title":"Enhancing Reinforcement Learning in Sensor Fusion: A Comparative Analysis of Cubature and Sampling-based Integration Methods for Rover Search Planning","created":"2024-05-14","cited_by_count":2,"area":"deeprl"},{"id":"2405.11784","title":"Reward-Punishment Reinforcement Learning with Maximum Entropy","created":"2024-05-20","cited_by_count":2,"area":"deeprl"},{"id":"2405.18289","title":"Highway Reinforcement Learning","created":"2024-05-28","cited_by_count":2,"area":"deeprl"},{"id":"2503.11019","title":"Residual Policy Gradient: A Reward View of KL-regularized Objective","created":"2025-03-14","cited_by_count":2,"area":"offlinerl"},{"id":"2505.22781","title":"Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean-Field Games","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2510.08526","title":"Convergence Theorems for Entropy-Regularized and Distributional Reinforcement Learning","created":"2025-10-09","cited_by_count":2,"area":"deeprl"},{"id":"2511.11592","title":"Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RL","created":"2025-10-25","cited_by_count":2,"area":"deeprl"},{"id":"2512.21527","title":"Generative Actor Critic","created":"2025-12-25","cited_by_count":2,"area":"deeprl"},{"id":"2103.06617","title":"A Quadratic Actor Network for Model-Free Reinforcement Learning","created":"2021-03-11","cited_by_count":1,"area":null},{"id":"2103.09756","title":"Near Optimal Policy Optimization via REPS","created":"2021-03-17","cited_by_count":1,"area":null},{"id":"2110.10934","title":"Can Q-learning solve Multi Armed Bantids?","created":"2021-10-21","cited_by_count":1,"area":null},{"id":"2111.14204","title":"Count-Based Temperature Scheduling for Maximum Entropy Reinforcement Learning","created":"2021-11-28","cited_by_count":1,"area":null},{"id":"2204.04292","title":"Evolving Pareto-Optimal Actor-Critic Algorithms for Generalizability and Stability","created":"2022-04-08","cited_by_count":1,"area":null},{"id":"2206.10736","title":"Imitate then Transcend: Multi-Agent Optimal Execution with Dual-Window Denoise PPO","created":"2022-06-21","cited_by_count":1,"area":null},{"id":"2209.01693","title":"Variational Inference for Model-Free and Model-Based Reinforcement Learning","created":"2022-09-04","cited_by_count":1,"area":null},{"id":"2406.05953","title":"Decoupling regularization from the action space","created":"2024-06-10","cited_by_count":1,"area":"deeprl"},{"id":"2408.09493","title":"Ancestral Reinforcement Learning: Unifying Zeroth-Order Optimization and Genetic Algorithms for Reinforcement Learning","created":"2024-08-18","cited_by_count":1,"area":"deeprl"},{"id":"2506.10871","title":"Viability of Future Actions: Robust Safety in Reinforcement Learning via Entropy Regularization","created":"2025-06-12","cited_by_count":1,"area":"deeprl"},{"id":"2601.18840","title":"Bellman Residual Minimization for Control: Geometry, Stationarity, and Convergence","created":"2026-01-26","cited_by_count":1,"area":null}],"next_cursor":"100"}