{"total":176,"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":"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":"2302.05446","title":"Robust Scheduling with GFlowNets","created":"2023-01-17","cited_by_count":69,"area":null},{"id":"2111.11188","title":"Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification","created":"2021-11-22","cited_by_count":61,"area":"offlinerl"},{"id":"2102.04376","title":"Adversarially Guided Actor-Critic","created":"2021-02-08","cited_by_count":47,"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":"2505.23433","title":"Diversity-Aware Policy Optimization for Large Language Model Reasoning","created":"2025-05-29","cited_by_count":41,"area":"lr"},{"id":"2106.10268","title":"MADE: Exploration via Maximizing Deviation from Explored Regions","created":"2021-06-18","cited_by_count":40,"area":null},{"id":"2509.03493","title":"On Entropy Control in LLM-RL Algorithms","created":"2025-09-03","cited_by_count":40,"area":null},{"id":"2509.15207","title":"FlowRL: Matching Reward Distributions for LLM Reasoning","created":"2025-09-18","cited_by_count":40,"area":"lr"},{"id":"2106.00285","title":"Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning","created":"2021-06-01","cited_by_count":38,"area":null},{"id":"2505.23585","title":"On-Policy RL with Optimal Reward Baseline","created":"2025-05-29","cited_by_count":34,"area":"lr"},{"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":"2504.19599","title":"GVPO: Group Variance Policy Optimization for Large Language Model Post-Training","created":"2025-04-28","cited_by_count":32,"area":"alignment"},{"id":"2112.14582","title":"A Statistical Analysis of Polyak-Ruppert Averaged Q-learning","created":"2021-12-29","cited_by_count":29,"area":null},{"id":"2310.20703","title":"Vanishing Gradients in Reinforcement Finetuning of Language Models","created":"2023-10-31","cited_by_count":27,"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":"2305.14502","title":"RetICL: Sequential Retrieval of In-Context Examples with Reinforcement Learning","created":"2023-05-23","cited_by_count":24,"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":"2509.20712","title":"CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning","created":"2025-09-25","cited_by_count":23,"area":"lr"},{"id":"2203.12592","title":"Your Policy Regularizer is Secretly an Adversary","created":"2022-03-23","cited_by_count":21,"area":null},{"id":"2202.06618","title":"A Differential Entropy Estimator for Training Neural Networks","created":"2022-02-14","cited_by_count":20,"area":null},{"id":"2206.00833","title":"Finite-Time Analysis of Entropy-Regularized Neural Natural Actor-Critic Algorithm","created":"2022-06-02","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":"2411.15370","title":"Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers","created":"2024-11-22","cited_by_count":18,"area":"deeprl"},{"id":"2501.19358","title":"The Energy Loss Phenomenon in RLHF: A New Perspective on Mitigating Reward Hacking","created":"2025-01-31","cited_by_count":18,"area":"alignment"},{"id":"2202.00308","title":"PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation","created":"2022-02-01","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":"2112.11921","title":"Variational Quantum Soft Actor-Critic","created":"2021-12-20","cited_by_count":15,"area":null},{"id":"2212.07536","title":"Robust Policy Optimization in Deep Reinforcement Learning","created":"2022-12-14","cited_by_count":15,"area":null},{"id":"2311.14168","title":"Fast Policy Learning for Linear Quadratic Control with Entropy Regularization","created":"2023-11-23","cited_by_count":13,"area":null},{"id":"2409.06290","title":"EntAugment: Entropy-Driven Adaptive Data Augmentation Framework for Image Classification","created":"2024-09-10","cited_by_count":13,"area":null},{"id":"2405.02235","title":"Learning Optimal Deterministic Policies with Stochastic Policy Gradients","created":"2024-05-03","cited_by_count":12,"area":"deeprl"},{"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":"2104.11706","title":"Safe Chance Constrained Reinforcement Learning for Batch Process Control","created":"2021-04-23","cited_by_count":11,"area":null},{"id":"2309.14597","title":"Policy Optimization in a Noisy Neighborhood: On Return Landscapes in Continuous Control","created":"2023-09-26","cited_by_count":11,"area":null},{"id":"2509.22611","title":"Quantile Advantage Estimation: Stabilizing RLVR for LLM Reasoning","created":"2025-09-26","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":"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":"2410.22093","title":"PC-Gym: Benchmark Environments For Process Control Problems","created":"2024-10-29","cited_by_count":10,"area":"deeprl"},{"id":"2501.16918","title":"On Rollouts in Model-Based Reinforcement Learning","created":"2025-01-28","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":"2510.01656","title":"Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning","created":"2025-10-02","cited_by_count":10,"area":"lr"},{"id":"2112.11622","title":"An Alternate Policy Gradient Estimator for Softmax Policies","created":"2021-12-22","cited_by_count":9,"area":null},{"id":"2402.07808","title":"Sourcerer: Sample-based Maximum Entropy Source Distribution Estimation","created":"2024-02-12","cited_by_count":9,"area":null},{"id":"2410.05255","title":"Bridging SFT and DPO for Diffusion Model Alignment with Self-Sampling Preference Optimization","created":"2024-10-07","cited_by_count":9,"area":"diffusion"},{"id":"2502.08208","title":"Exploring Exploration in Bayesian Optimization","created":"2025-02-12","cited_by_count":9,"area":null},{"id":"2510.18460","title":"Learning Boltzmann Generators via Constrained Mass Transport","created":"2025-10-21","cited_by_count":9,"area":null},{"id":"2110.01212","title":"Inducing Equilibria via Incentives: Simultaneous Design-and-Play Ensures Global Convergence","created":"2021-10-04","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":"2405.18221","title":"Recurrent Natural Policy Gradient for POMDPs","created":"2024-05-28","cited_by_count":8,"area":"deeprl"},{"id":"2501.11533","title":"The impact of intrinsic rewards on exploration in Reinforcement Learning","created":"2025-01-20","cited_by_count":8,"area":"deeprl"},{"id":"2503.00799","title":"On Generalization Across Environments In Multi-Objective Reinforcement Learning","created":"2025-03-02","cited_by_count":8,"area":"deeprl"},{"id":"2602.03392","title":"On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models","created":"2026-02-03","cited_by_count":8,"area":null},{"id":"2102.06042","title":"Modeling the Interaction between Agents in Cooperative Multi-Agent Reinforcement Learning","created":"2021-02-10","cited_by_count":7,"area":null},{"id":"2305.05586","title":"RLocator: Reinforcement Learning for Bug Localization","created":"2023-05-09","cited_by_count":7,"area":null},{"id":"2405.13136","title":"Towards Principled, Practical Policy Gradient for Bandits and Tabular MDPs","created":"2024-05-21","cited_by_count":7,"area":"deeprl"},{"id":"2505.03209","title":"DYSTIL: Dynamic Strategy Induction with Large Language Models for Reinforcement Learning","created":"2025-05-06","cited_by_count":7,"area":"offlinerl"},{"id":"2506.05615","title":"When Maximum Entropy Misleads Policy Optimization","created":"2025-06-05","cited_by_count":7,"area":"deeprl"},{"id":"2008.07284","title":"Forward and inverse reinforcement learning sharing network weights and hyperparameters","created":"2020-08-17","cited_by_count":6,"area":"offlinerl"},{"id":"2201.12434","title":"Do You Need the Entropy Reward (in Practice)?","created":"2022-01-28","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":"2405.01616","title":"Generative Active Learning for the Search of Small-molecule Protein Binders","created":"2024-05-02","cited_by_count":6,"area":null},{"id":"2506.07085","title":"State Entropy Regularization for Robust Reinforcement Learning","created":"2025-06-08","cited_by_count":6,"area":"deeprl"},{"id":"2605.19461","title":"Beyond Mode Collapse: Distribution Matching for Diverse Reasoning","created":"2026-05-19","cited_by_count":6,"area":"lr"},{"id":"2111.08172","title":"Off-Policy Actor-Critic with Emphatic Weightings","created":"2021-11-16","cited_by_count":5,"area":null},{"id":"2412.16848","title":"ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning","created":"2024-12-22","cited_by_count":5,"area":"offlinerl"},{"id":"2506.18330","title":"Confucius3-Math: A Lightweight High-Performance Reasoning LLM for Chinese K-12 Mathematics Learning","created":"2025-06-23","cited_by_count":5,"area":"lr"},{"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":"2601.21669","title":"Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling","created":"2026-01-29","cited_by_count":5,"area":"deeprl"},{"id":"2603.02155","title":"Near-Optimal Regret for KL-Regularized Multi-Armed Bandits","created":"2026-03-02","cited_by_count":5,"area":null},{"id":"2109.10883","title":"ENERO: Efficient Real-Time WAN Routing Optimization with Deep Reinforcement Learning","created":"2021-09-22","cited_by_count":4,"area":null},{"id":"2209.06259","title":"Designing Biological Sequences via Meta-Reinforcement Learning and Bayesian Optimization","created":"2022-09-13","cited_by_count":4,"area":null},{"id":"2209.14513","title":"How Does Return Distribution in Distributional Reinforcement Learning Help Optimization?","created":"2022-09-29","cited_by_count":4,"area":null},{"id":"2301.12038","title":"STEERING: Stein Information Directed Exploration for Model-Based Reinforcement Learning","created":"2023-01-28","cited_by_count":4,"area":null},{"id":"2305.06851","title":"Policy Gradient Algorithms Implicitly Optimize by Continuation","created":"2023-05-11","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":"2408.00309","title":"Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning","created":"2024-08-01","cited_by_count":4,"area":"deeprl"},{"id":"2409.04744","title":"Reward Guidance for Reinforcement Learning Tasks Based on Large Language Models: The LMGT Framework","created":"2024-09-07","cited_by_count":4,"area":null},{"id":"2102.06808","title":"Planning and Learning Using Adaptive Entropy Tree Search","created":"2021-02-12","cited_by_count":3,"area":null},{"id":"2106.12194","title":"Uncertainty-Aware Model-Based Reinforcement Learning with Application to Autonomous Driving","created":"2021-06-23","cited_by_count":3,"area":"driving"},{"id":"2107.05217","title":"Cautious Actor-Critic","created":"2021-07-12","cited_by_count":3,"area":null},{"id":"2110.02398","title":"Approximate Newton policy gradient algorithms","created":"2021-10-05","cited_by_count":3,"area":null},{"id":"2112.00940","title":"Reward-Free Attacks in Multi-Agent Reinforcement Learning","created":"2021-12-02","cited_by_count":3,"area":null},{"id":"2210.14685","title":"Leveraging Demonstrations with Latent Space Priors","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2211.11869","title":"Examining Policy Entropy of Reinforcement Learning Agents for Personalization Tasks","created":"2022-11-21","cited_by_count":3,"area":null},{"id":"2302.03364","title":"Population-size-Aware Policy Optimization for Mean-Field Games","created":"2023-02-07","cited_by_count":3,"area":null},{"id":"2303.14966","title":"Adaptive Federated Learning via New Entropy Approach","created":"2023-03-27","cited_by_count":3,"area":null},{"id":"2402.00162","title":"Behind the Myth of Exploration in Policy Gradients","created":"2024-01-31","cited_by_count":3,"area":"deeprl"},{"id":"2406.17334","title":"Joint Admission Control and Resource Allocation of Virtual Network Embedding via Hierarchical Deep Reinforcement Learning","created":"2024-06-25","cited_by_count":3,"area":"deeprl"},{"id":"2406.19825","title":"Reinforcement Learning for Efficient Design and Control Co-optimisation of Energy Systems","created":"2024-06-28","cited_by_count":3,"area":"deeprl"},{"id":"2410.13060","title":"AERO: Entropy-Guided Framework for Private LLM Inference","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2412.06655","title":"Off-Policy Maximum Entropy RL with Future State and Action Visitation Measures","created":"2024-12-09","cited_by_count":3,"area":"deeprl"},{"id":"2501.17115","title":"Evidence on the Regularisation Properties of Maximum-Entropy Reinforcement Learning","created":"2025-01-28","cited_by_count":3,"area":"deeprl"},{"id":"2509.23183","title":"ZeroSiam: An Efficient Asymmetry for Test-Time Entropy Optimization without Collapse","created":"2025-09-27","cited_by_count":3,"area":"lr"},{"id":"2510.25529","title":"Off-policy Reinforcement Learning with Model-based Exploration Augmentation","created":"2025-10-29","cited_by_count":3,"area":"deeprl"},{"id":"2511.22581","title":"High entropy leads to symmetry-equivariant policies in Dec-POMDPs","created":"2025-11-27","cited_by_count":3,"area":"deeprl"},{"id":"2201.05560","title":"Demystifying Reinforcement Learning in Time-Varying Systems","created":"2022-01-14","cited_by_count":2,"area":null},{"id":"2202.07496","title":"Beyond the Policy Gradient Theorem for Efficient Policy Updates in Actor-Critic Algorithms","created":"2022-02-15","cited_by_count":2,"area":null}],"next_cursor":"100"}