{"total":69,"rows":[{"id":"2110.01515","title":"A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning","created":"2021-10-04","cited_by_count":82,"area":null},{"id":"2405.19320","title":"Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF","created":"2024-05-29","cited_by_count":73,"area":"alignment"},{"id":"2106.12059","title":"Stochastic Batch Acquisition: A Simple Baseline for Deep Active Learning","created":"2021-06-22","cited_by_count":36,"area":null},{"id":"2307.16212","title":"Robust Multi-Agent Reinforcement Learning with State Uncertainty","created":"2023-07-30","cited_by_count":36,"area":null},{"id":"2206.13102","title":"Modeling Content Creator Incentives on Algorithm-Curated Platforms","created":"2022-06-27","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":"2412.12098","title":"MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization","created":"2024-12-16","cited_by_count":30,"area":"deeprl"},{"id":"2209.08890","title":"An information-theoretic perspective on intrinsic motivation in reinforcement learning: a survey","created":"2022-09-19","cited_by_count":28,"area":null},{"id":"2305.20065","title":"Latent Exploration for Reinforcement Learning","created":"2023-05-31","cited_by_count":22,"area":null},{"id":"2502.01618","title":"Rollout Roulette: A Probabilistic Inference Approach to Inference-Time Scaling of LLMs using Particle-Based Monte Carlo Methods","created":"2025-02-03","cited_by_count":20,"area":"lr"},{"id":"2111.03290","title":"Maillard Sampling: Boltzmann Exploration Done Optimally","created":"2021-11-05","cited_by_count":13,"area":null},{"id":"2502.05378","title":"NextBestPath: Efficient 3D Mapping of Unseen Environments","created":"2025-02-07","cited_by_count":13,"area":null},{"id":"2310.03912","title":"RTDK-BO: High Dimensional Bayesian Optimization with Reinforced Transformer Deep kernels","created":"2023-10-05","cited_by_count":11,"area":null},{"id":"2402.17722","title":"Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergence","created":"2024-02-27","cited_by_count":11,"area":null},{"id":"2310.18591","title":"Inverse Decision Modeling: Learning Interpretable Representations of Behavior","created":"2023-10-28","cited_by_count":10,"area":null},{"id":"2402.17235","title":"Stochastic Gradient Succeeds for Bandits","created":"2024-02-27","cited_by_count":10,"area":null},{"id":"2205.04424","title":"Accelerated Reinforcement Learning for Temporal Logic Control Objectives","created":"2022-05-09","cited_by_count":9,"area":null},{"id":"2302.01223","title":"Practical Bandits: An Industry Perspective","created":"2023-02-02","cited_by_count":9,"area":null},{"id":"2312.03814","title":"Pearl: A Production-ready Reinforcement Learning Agent","created":"2023-12-06","cited_by_count":9,"area":null},{"id":"2508.12116","title":"DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collections","created":"2025-08-16","cited_by_count":9,"area":null},{"id":"2102.07800","title":"Top-$k$ eXtreme Contextual Bandits with Arm Hierarchy","created":"2021-02-15","cited_by_count":8,"area":null},{"id":"2107.00833","title":"Quantifying Availability and Discovery in Recommender Systems via Stochastic Reachability","created":"2021-06-30","cited_by_count":8,"area":null},{"id":"2511.20066","title":"SOMBRL: Scalable and Optimistic Model-Based RL","created":"2025-11-25","cited_by_count":7,"area":"deeprl"},{"id":"2208.04466","title":"Optimal scheduling of entropy regulariser for continuous-time linear-quadratic reinforcement learning","created":"2022-08-08","cited_by_count":6,"area":null},{"id":"2301.11135","title":"FedHQL: Federated Heterogeneous Q-Learning","created":"2023-01-26","cited_by_count":6,"area":null},{"id":"2407.13755","title":"Random Latent Exploration for Deep Reinforcement Learning","created":"2024-07-18","cited_by_count":6,"area":"deeprl"},{"id":"2107.00877","title":"Conflict-free collective stochastic decision making by orbital angular momentum of photons through quantum interference","created":"2021-07-02","cited_by_count":5,"area":null},{"id":"2410.12136","title":"Sample-Efficient Reinforcement Learning with Temporal Logic Objectives: Leveraging the Task Specification to Guide Exploration","created":"2024-10-16","cited_by_count":5,"area":"deeprl"},{"id":"2502.19859","title":"IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic","created":"2025-02-27","cited_by_count":5,"area":"offlinerl"},{"id":"2507.17668","title":"How Should We Meta-Learn Reinforcement Learning Algorithms?","created":"2025-07-23","cited_by_count":5,"area":"deeprl"},{"id":"2405.03865","title":"Information-driven Affordance Discovery for Efficient Robotic Manipulation","created":"2024-05-06","cited_by_count":4,"area":null},{"id":"2501.15034","title":"Divergence-Augmented Policy Optimization","created":"2025-01-25","cited_by_count":4,"area":"deeprl"},{"id":"1803.00444","title":"Inverse Reinforcement Learning via Nonparametric Spatio-Temporal Subgoal Modeling","created":"2018-03-01","cited_by_count":3,"area":"offlinerl"},{"id":"2406.05710","title":"Data-Driven Upper Confidence Bounds with Near-Optimal Regret for Heavy-Tailed Bandits","created":"2024-06-09","cited_by_count":3,"area":null},{"id":"2407.20917","title":"How to Choose a Reinforcement-Learning Algorithm","created":"2024-07-30","cited_by_count":3,"area":"deeprl"},{"id":"2507.00518","title":"Exploring Large Action Sets with Hyperspherical Embeddings using von Mises-Fisher Sampling","created":"2025-07-01","cited_by_count":3,"area":"deeprl"},{"id":"2510.24482","title":"Sample-efficient and Scalable Exploration in Continuous-Time RL","created":"2025-10-28","cited_by_count":3,"area":"deeprl"},{"id":"2604.15614","title":"Flexible Empowerment at Reasoning with Extended Best-of-N Sampling","created":"2026-04-17","cited_by_count":3,"area":null},{"id":"2101.00738","title":"A novel policy for pre-trained Deep Reinforcement Learning for Speech Emotion Recognition","created":"2021-01-04","cited_by_count":2,"area":null},{"id":"2105.08666","title":"Reinforcement Learning With Sparse-Executing Actions via Sparsity Regularization","created":"2021-05-18","cited_by_count":2,"area":null},{"id":"2304.14989","title":"Kullback-Leibler Maillard Sampling for Multi-armed Bandits with Bounded Rewards","created":"2023-04-28","cited_by_count":2,"area":null},{"id":"2507.14444","title":"Statistical and Algorithmic Foundations of Reinforcement Learning","created":"2025-07-19","cited_by_count":2,"area":"deeprl"},{"id":"2507.16356","title":"Learning to Call: A Field Trial of a Collaborative Bandit Algorithm for Improved Message Delivery in Mobile Maternal Health","created":"2025-07-22","cited_by_count":2,"area":null},{"id":"2103.03450","title":"DeepFreight: Integrating Deep Reinforcement Learning and Mixed Integer Programming for Multi-transfer Truck Freight Delivery","created":"2021-03-05","cited_by_count":1,"area":null},{"id":"2106.07502","title":"Training like Playing: A Reinforcement Learning And Knowledge Graph-based framework for building Automatic Consultation System in Medical Field","created":"2021-06-14","cited_by_count":1,"area":null},{"id":"2210.06302","title":"Maximum entropy exploration in contextual bandits with neural networks and energy based models","created":"2022-10-12","cited_by_count":1,"area":null},{"id":"2306.11982","title":"Balanced Mixture of SuperNets for Learning the CNN Pooling Architecture","created":"2023-06-21","cited_by_count":1,"area":null},{"id":"2310.10818","title":"Uncertainty-aware transfer across tasks using hybrid model-based successor feature reinforcement learning","created":"2023-10-16","cited_by_count":1,"area":null},{"id":"2311.00096","title":"Bandit-Driven Batch Selection for Robust Learning under Label Noise","created":"2023-10-31","cited_by_count":1,"area":null},{"id":"2402.03136","title":"Mastering Zero-Shot Interactions in Cooperative and Competitive Simultaneous Games","created":"2024-02-05","cited_by_count":1,"area":null},{"id":"2403.19946","title":"A Peg-in-hole Task Strategy for Holes in Concrete","created":"2024-03-29","cited_by_count":1,"area":null},{"id":"2407.20506","title":"Boosting Efficiency in Task-Agnostic Exploration through Causal Knowledge","created":"2024-07-30","cited_by_count":1,"area":"wm"},{"id":"2506.08737","title":"Exploration by Random Reward Perturbation","created":"2025-06-10","cited_by_count":1,"area":"deeprl"},{"id":"2602.16274","title":"Regret and Sample Complexity of Online Q-Learning via Concentration of Stochastic Approximation with Time-Inhomogeneous Markov Chains","created":"2026-02-18","cited_by_count":1,"area":"deeprl"},{"id":"2604.06938","title":"POS-ISP: Pipeline Optimization at the Sequence Level for Task-aware ISP","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2104.12827","title":"Learning-based decentralized offloading decision making in an adversarial environment","created":"2021-04-26","cited_by_count":0,"area":null},{"id":"2110.02919","title":"Residual Overfit Method of Exploration","created":"2021-10-06","cited_by_count":0,"area":null},{"id":"2308.01028","title":"Maximizing Success Rate of Payment Routing using Non-stationary Bandits","created":"2023-08-02","cited_by_count":0,"area":null},{"id":"2402.11835","title":"Easy as ABCs: Unifying Boltzmann Q-Learning and Counterfactual Regret Minimization","created":"2024-02-19","cited_by_count":0,"area":"deeprl"},{"id":"2410.21405","title":"Bayesian Collaborative Bandits with Thompson Sampling for Improved Outreach in Maternal Health Program","created":"2024-10-28","cited_by_count":0,"area":null},{"id":"2501.00562","title":"An Overview and Discussion on Using Large Language Models for Implementation Generation of Solutions to Open-Ended Problems","created":"2024-12-31","cited_by_count":0,"area":null},{"id":"2503.21061","title":"Neural Architecture Search by Learning a Hierarchical Search Space","created":"2025-03-27","cited_by_count":0,"area":null},{"id":"2506.06786","title":"Learning What Matters Now: A Dual-Critic Context-Aware RL Framework for Priority-Driven Information Gain","created":"2025-06-07","cited_by_count":0,"area":"deeprl"},{"id":"2511.08717","title":"Optimal control of the future via prospective learning with control","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2511.10501","title":"Graph Neural Networks, Deep Reinforcement Learning and Probabilistic Topic Modeling for Strategic Multiagent Settings","created":"2025-11-13","cited_by_count":0,"area":null},{"id":"2602.16315","title":"The Diversity Paradox revisited: Systemic Effects of Feedback Loops in Recommender Systems","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.02154","title":"Boltzmann-based Exploration for Robust Decentralized Multi-Agent Planning (Extended Version)","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2605.31034","title":"Annealed Softmax Greedy in Many-Armed Bayesian Bandits","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.30228","title":"B3O: Scalable Boltzmann Batch Bayesian Optimization","created":"2026-06-29","cited_by_count":0,"area":null}],"next_cursor":null}