{"total":182,"rows":[{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176,"area":null},{"id":"2301.02328","title":"Extreme Q-Learning: MaxEnt RL without Entropy","created":"2023-01-05","cited_by_count":116,"area":"offlinerl"},{"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":"2405.21046","title":"Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF","created":"2024-05-31","cited_by_count":106,"area":"alignment"},{"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":"2102.01585","title":"Approximately Solving Mean Field Games via Entropy-Regularized Deep Reinforcement Learning","created":"2021-02-02","cited_by_count":73,"area":null},{"id":"2109.00157","title":"A Survey of Exploration Methods in Reinforcement Learning","created":"2021-09-01","cited_by_count":73,"area":null},{"id":"2502.00361","title":"Efficient Online Reinforcement Learning for Diffusion Policy","created":"2025-02-01","cited_by_count":71,"area":"diffusion"},{"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":"2502.02316","title":"DIME:Diffusion-Based Maximum Entropy Reinforcement Learning","created":"2025-02-04","cited_by_count":58,"area":"diffusion"},{"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":"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":"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":"2106.10268","title":"MADE: Exploration via Maximizing Deviation from Explored Regions","created":"2021-06-18","cited_by_count":40,"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":"2110.00641","title":"Batch size-invariance for policy optimization","created":"2021-10-01","cited_by_count":35,"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":"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":"2102.08940","title":"Near-optimal Policy Optimization Algorithms for Learning Adversarial Linear Mixture MDPs","created":"2021-02-17","cited_by_count":28,"area":null},{"id":"2207.00046","title":"Performative Reinforcement Learning","created":"2022-06-30","cited_by_count":27,"area":null},{"id":"2105.08158","title":"The Confluence of Networks, Games and Learning","created":"2021-05-17","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":"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":"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":"2111.00552","title":"Policy Optimization for Constrained MDPs with Provable Fast Global Convergence","created":"2021-10-31","cited_by_count":23,"area":null},{"id":"2211.16715","title":"Policy Optimization over General State and Action Spaces","created":"2022-11-30","cited_by_count":23,"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":"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":"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":"2205.13746","title":"Regularized Gradient Descent Ascent for Two-Player Zero-Sum Markov Games","created":"2022-05-27","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":"2305.12944","title":"Offline Primal-Dual Reinforcement Learning for Linear MDPs","created":"2023-05-22","cited_by_count":17,"area":"offlinerl"},{"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":"2306.00629","title":"Identifiability and Generalizability in Constrained Inverse Reinforcement Learning","created":"2023-06-01","cited_by_count":16,"area":"offlinerl"},{"id":"2105.04321","title":"Reinforcement learning of rare diffusive dynamics","created":"2021-05-10","cited_by_count":15,"area":null},{"id":"2110.00304","title":"Divergence-Regularized Multi-Agent Actor-Critic","created":"2021-10-01","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":"2201.09457","title":"Homotopic Policy Mirror Descent: Policy Convergence, Implicit Regularization, and Improved Sample Complexity","created":"2022-01-24","cited_by_count":14,"area":null},{"id":"2410.15474","title":"Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization","created":"2024-10-20","cited_by_count":14,"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":"2210.00999","title":"Latent State Marginalization as a Low-cost Approach for Improving Exploration","created":"2022-10-03","cited_by_count":13,"area":null},{"id":"2305.11032","title":"Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL","created":"2023-05-18","cited_by_count":13,"area":null},{"id":"2402.16181","title":"How Can LLM Guide RL? A Value-Based Approach","created":"2024-02-25","cited_by_count":13,"area":null},{"id":"2211.02105","title":"Geometry and convergence of natural policy gradient methods","created":"2022-11-03","cited_by_count":12,"area":null},{"id":"2104.11706","title":"Safe Chance Constrained Reinforcement Learning for Batch Process Control","created":"2021-04-23","cited_by_count":11,"area":null},{"id":"2201.05756","title":"Block Policy Mirror Descent","created":"2022-01-15","cited_by_count":11,"area":null},{"id":"2311.13294","title":"Probabilistic Inference in Reinforcement Learning Done Right","created":"2023-11-22","cited_by_count":11,"area":null},{"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":"2102.06234","title":"Optimization Issues in KL-Constrained Approximate Policy Iteration","created":"2021-02-11","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":"2302.09339","title":"Efficient Exploration via Epistemic-Risk-Seeking Policy Optimization","created":"2023-02-18","cited_by_count":10,"area":null},{"id":"2307.09470","title":"Multi-Player Zero-Sum Markov Games with Networked Separable Interactions","created":"2023-07-13","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":"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":"2309.08571","title":"A Bayesian Approach to Robust Inverse Reinforcement Learning","created":"2023-09-15","cited_by_count":9,"area":"offlinerl"},{"id":"2310.17303","title":"Demonstration-Regularized RL","created":"2023-10-26","cited_by_count":9,"area":"alignment"},{"id":"2210.12057","title":"Efficient Global Planning in Large MDPs via Stochastic Primal-Dual Optimization","created":"2022-10-21","cited_by_count":8,"area":null},{"id":"2210.12812","title":"Symmetric (Optimistic) Natural Policy Gradient for Multi-agent Learning with Parameter Convergence","created":"2022-10-23","cited_by_count":8,"area":null},{"id":"2302.14004","title":"Optimistic Planning by Regularized Dynamic Programming","created":"2023-02-27","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":"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":"2109.11792","title":"Regularization Guarantees Generalization in Bayesian Reinforcement Learning through Algorithmic Stability","created":"2021-09-24","cited_by_count":7,"area":null},{"id":"2203.08542","title":"Lazy-MDPs: Towards Interpretable Reinforcement Learning by Learning When to Act","created":"2022-03-16","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":"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":"2106.04443","title":"Robust Generalization despite Distribution Shift via Minimum Discriminating Information","created":"2021-06-08","cited_by_count":6,"area":null},{"id":"2204.09424","title":"SAAC: Safe Reinforcement Learning as an Adversarial Game of Actor-Critics","created":"2022-04-20","cited_by_count":6,"area":null},{"id":"2305.15277","title":"Successor-Predecessor Intrinsic Exploration","created":"2023-05-24","cited_by_count":6,"area":null},{"id":"2306.14133","title":"Provably Convergent Policy Optimization via Metric-aware Trust Region Methods","created":"2023-06-25","cited_by_count":6,"area":null},{"id":"2406.04056","title":"Bisimulation Metrics are Optimal Transport Distances, and Can be Computed Efficiently","created":"2024-06-06","cited_by_count":6,"area":null},{"id":"2501.09080","title":"Average-Reward Soft Actor-Critic","created":"2025-01-15","cited_by_count":6,"area":"deeprl"},{"id":"2506.01541","title":"Adaptive Destruction Processes for Diffusion Samplers","created":"2025-06-02","cited_by_count":6,"area":"diffusion"},{"id":"2506.07085","title":"State Entropy Regularization for Robust Reinforcement Learning","created":"2025-06-08","cited_by_count":6,"area":"deeprl"},{"id":"2512.20576","title":"Performative Policy Gradient: Optimality in Performative Reinforcement Learning","created":"2025-12-23","cited_by_count":6,"area":"deeprl"},{"id":"2512.22716","title":"Memento 2: Learning by Stateful Reflective Memory","created":"2025-12-27","cited_by_count":6,"area":"agents"},{"id":"2403.19448","title":"Fisher-Rao Gradient Flows of Linear Programs and State-Action Natural Policy Gradients","created":"2024-03-28","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":"2409.19437","title":"Strongly-polynomial time and validation analysis of policy gradient methods","created":"2024-09-28","cited_by_count":5,"area":"deeprl"},{"id":"2602.23116","title":"Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences","created":"2026-02-26","cited_by_count":5,"area":"alignment"},{"id":"2603.02155","title":"Near-Optimal Regret for KL-Regularized Multi-Armed Bandits","created":"2026-03-02","cited_by_count":5,"area":null},{"id":"2209.04067","title":"RASR: Risk-Averse Soft-Robust MDPs with EVaR and Entropic Risk","created":"2022-09-09","cited_by_count":4,"area":null},{"id":"2401.06566","title":"Maximum Causal Entropy IRL in Mean-Field Games and GNEP Framework for Forward RL","created":"2024-01-12","cited_by_count":4,"area":"offlinerl"},{"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":"2412.14002","title":"Operator Splitting for Convex Constrained Markov Decision Processes","created":"2024-12-18","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":"2110.02398","title":"Approximate Newton policy gradient algorithms","created":"2021-10-05","cited_by_count":3,"area":null},{"id":"2312.12869","title":"Parameterized Projected Bellman Operator","created":"2023-12-20","cited_by_count":3,"area":null},{"id":"2403.06366","title":"Finite-Time Error Analysis of Soft Q-Learning: Switching System Approach","created":"2024-03-11","cited_by_count":3,"area":"deeprl"},{"id":"2407.03995","title":"ROER: Regularized Optimal Experience Replay","created":"2024-07-04","cited_by_count":3,"area":"deeprl"}],"next_cursor":"100"}