Sample-Efficient RL

RL: Reinforcement Learning

Follow this topic Ask about this topic

Momentum

12 papers in the last four weeks, up 140% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 168

All topics

LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Models
Jul 30, 2026Shuang Liang, Haoyang Zhou, Yifan Gong +2Numerical Reasoning in Language Models Reinforcement Learning with Verifiable Rewards
Renmin University of China · AntGroup
Early Verdicts, Better Budgets: Sequential Adaptive Rollout Allocation for Compute-Efficient RLVR
Jul 28, 2026Pixel Nomand, Elena Voss, Marcus Hale +1Reinforcement Learning RL for Language Model Reasoning
University of Wisconsin–Madison · University of Washington
When Every Simulation Counts: Value-Based Reinforcement Learning for Accelerated Photonics Inverse Design
Jul 26, 2026Longying Wen, Feiyang Wu, Jinglin Yu +3Deep Q-Learning Sample-Efficient RL
School of Science and Engineering The Chinese University of Hong Kong, Shenzhen Shenzhen, China · Nick Holonyak Micro and Nanotechnology Laboratory University of Illinois Urbana-Champaign Urbana, Illinois, USA
Learning as Reasoning Unfolds: Progressive Rollout Allocation for Efficient Reinforcement Learning
Jul 24, 2026Heyang Jiang, Henry Liu, Baharan MirzasoleimanRL for Code Generation RL for Language Model Reasoning
University of California, Los Angeles
Expert Behavior Prior Reinforcement Learning
Jul 23, 2026Gong Gao, Weidong Zhao, Xianhui Liu +1RL Control Reinforcement Learning
School of Computer Science, Tongji University, China
Sample-Efficient Learning from Agent Experience
Jul 23, 2026Chenhui Gou, Haoqin Tu, Yunhao Fang +2In-Context RL Language Model Distillation
Monash University · ByteDance Seed
Theoretical Foundations of $\max$ @ $k$ Reinforcement Learning
Jul 20, 2026Riccardo Poiani, Martino Bernasconi, Andrea CelliReinforcement Learning Policy Learning
Bocconi University
Rethinking the Suitability of Reinforcement Learning Algorithms Under Practical Transfer Constraints
Jul 19, 2026Hany Hamed, Abhishek Naik, Colin Bellinger +1Domain Randomization Reinforcement Learning
University of Alberta · 3Alberta Machine Intelligence Institute (Amii) · 7Generative Bionics +4
Non-Asymptotic Best Policy Identification Guarantees in Online Reinforcement Learning
Jul 19, 2026Joseph Lazzaro, Alessio Russo, Aldo PacchianoMarkov Decision Processes RL Exploration
Imperial College London · Boston University · Broad Institute of MIT and Harvard
Lighthouse RL: Sample-Efficient Circuit Optimization via Strategic Reset Points
Jul 15, 2026Mustafa Emre Gürsoy, Stefan Uhlich, Ryoga Matsuo +6Reinforcement Learning Black-Box Optimization
1Sony Group Corporation, Switzerland · 2EPFL, Switzerland · 3Sony Semiconductor Solutions, Japan +1
Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement Learning
Jul 15, 2026Bowei He, Yankai Chen, Xiaokun Zhang +1Reinforcement Learning Policy Gradient Methods
Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE · McGill Univeristy, Montreal, Canada · City University of Hong Kong, Hong Kong SAR.
Factorized Spectral Representations for Reinforcement Learning
Jul 15, 2026Junyi Wu, Dan LiTensor Decomposition Representation Learning for RL
Department of Industrial and Systems Engineering University of Washington Seattle, WA, USA
ExToken: Structured Exploration for Efficient Vision-Language-Action Reinforcement Fine-tuning
Jul 14, 2026Yilun Kong, Yunpeng Qing, Guozheng Ma +4RL Exploration Robotic Manipulation
Nanyang Technological University · ACE Robotics · Zhejiang University +1
Knowledge- and Gradient-Guided Reinforcement Learning for Parametrized Action Markov Decision Processes
Jul 14, 2026Jonas Ehrhardt, René Heesch, Oliver NiggemannReinforcement Learning Constrained RL
Helmut-Schmidt-University, Hamburg, Germany
SCALECUA: Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RL
Jul 13, 2026Bowen Lv, Xiao Liu, Yanyu Ren +7Computer-Use Agents Reinforcement Learning with Verifiable Rewards
Tsinghua University
Prompt-Driven Exploration
Jul 9, 2026Sunshine Jiang, John Marangola, David Zhang +6LLM-Guided RL RL Exploration
Massachusetts Institute of Technology · Improbable AI Lab · MIT-IBM Computing Research Lab
Statistical Efficiency and Inference of Quantile Distributional Reinforcement Learning
Jul 9, 2026Zijie Cheng, Yang Peng, Zhihua ZhangDistributional RL Reinforcement Learning
School of Mathematical Sciences, Peking University · Yau Mathematical Sciences Center, Tsinghua University
Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF
Jul 8, 2026Eric Zhu, Abhinav Shrivastava, Soumik MukhopadhyayDiffusion Model Alignment RL for Diffusion Models
Carnegie Mellon University · University of Maryland, College Park
Mask-based Predictive Representations for Reinforcement Learning
Jul 5, 2026Kai ZhaoRepresentation Learning Predictive Representation Learning
School of Systems Science, Beijing Normal University · Beijing, China
Sample-Efficient Pareto Front Modeling for Energy-Aware Reinforcement Learning Using Bayesian Optimization
Jul 3, 2026Georg Schäfer, Jakob Rehrl, Stefan Huber +1RL Control Multi-Objective Reinforcement Learning
Josef Ressel Centre for Intelligent and Secure Industrial Automation, Salzburg University of Applied Sciences, Salzburg, Austria · Department of Artificial Intelligence and Human Interfaces, Paris Lodron University of Salzburg, Salzburg, Austria
WorldSample: Closed-loop Real-robot RL with World Modelling
Jul 2, 2026Yuquan Xue, Le Xu, Zeyi Liu +5Robot Skill Learning World Models for Robotics
1PINE Lab, School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore · Department of Electronic Engineering, Tsinghua University, Beijing, China · School of Automation, Central South University, Changsha, China +1
QuasiMoTTo: Quasi-Monte Carlo Test-Time Scaling
Jul 1, 2026Michael Y. Li, Anthony Zhan, Kanishk Gandhi +2Inference-Time Scaling Sample-Efficient RL
Stanford University
FastDSAC: Enhancing Policy Plasticity via Constrained Exploration for Scalable Humanoid Locomotion
Jun 30, 2026Guanchen Lu, Yajuan Dun, Yi Zhou +4Distributional RL Reinforcement Learning
Chongqing University, Chongqing 400044, China · Ministry of Industry and Information Technology, Beijing 100804, China · Tsinghua University, Beijing 100084, China +1
Hierarchical Reinforcement Learning in StarCraft Micromanagement with Influence Maps and Cluster-based Scripts
Jun 29, 2026Chunhui Bai, Changhe Li, Dequan Li +2Hierarchical RL Sparse-Reward RL
School of Artificial Intelligence and Automation, China University of Geosciences, Wuhan 430074, China · State Key Laboratory of Digital Intelligent Technology for Unmanned Coal Mining, Anhui University of Science & Technology, Huainan 232001, China · School of Artificial Intelligence, Anhui University of Science & Technology, Hefei 231131, China +1
Sample-efficient Transfer Reinforcement Learning via Adaptive Reward Shaping and Policy-Ratio Reweighting Strategy
Jun 25, 2026Wenjie Huang, Yang Li, Jingjia Teng +6Reinforcement Learning Reward Shaping
State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle, College of Mechanical and Vehicle Engineering, Hunan University, Changsha 410082, China · Key Laboratory of Intelligent Air-Ground Cooperative Control for Universities in Chongqing, School of Automation, Chongqing University of Posts and Telecommunications, Chongqing 400065, China · Xi’an Institute of High-Tech, Xi’an 710025, China +1
Mesh-RL: Coupled subgrid reinforcement learning
Jun 24, 2026Behnam Gheshlaghi, Bahador Rashidi, Shahin AtakishiyevReinforcement Learning Credit Assignment in RL
Independent Researcher · University of Alberta
Minimax PAC Bounds for Learning in Exogenous Contextual MDPs
Jun 23, 2026Corentin Pla, Hugo Richard, Marc Abeille +1Markov Decision Processes Reinforcement Learning
CREST, ENSAE · Criteo AI Lab · FairPlay Joint Team
Supervised Reinforcement Learning for the Coordination of Distributed Energy Resources
Jun 23, 2026Haoyuan Deng, Yihong Zhou, Thomas Morstyn +1Reinforcement Learning RL Fine-Tuning
The University of Hong Kong, Hong Kong SAR, China · University of Oxford, Oxford, U.K. · The University of Hong Kong Shenzhen Institute of Research and Innovation, Shenzhen, China
FAST: A Framework for Aligned Sampling and Training in Parallel Reinforcement Learning for Autonomous Driving
Jun 19, 2026Bonan Wang, Letian Tao, Bin Shuai +7Reinforcement Learning RL for Autonomous Driving
School of Vehicle and Mobility, Tsinghua University, Beijing 100084, China · Didi Voyager Labs, DiDi Autonomous Driving · School of Vehicle and Mobility and the College of AI, Tsinghua University, Beijing 100084, China
Backpropagating Through Simulation: Analytic Policy Gradients for Sample and Learning Efficient Differentiable Continuous Control
Jun 19, 2026Yueci DengRobotic RL Policy Gradient Methods
School of Data Science, The Chinese University of Hong Kong, Shenzhen

Jul 30, 2026, cs.CLJ/K move · Enter open · S save

LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Models

Shuang Liang, Haoyang Zhou, Yifan Gong, Guowei Wang+1

Renmin University of China · AntGroup

Numerical Reasoning in Language Models Reinforcement Learning with Verifiable Rewards Sample-Efficient RL

Open paper AskPDF arXiv

Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models, but prompt groups with identical rollout rewards consume generation budget without effective learning signals. Pre-rollout prompt selection can reduce this waste by screening prompts before rollout generation. However, existing pre-rollout methods struggle to balance exploitation and exploration: repeatedly exploiting historically informative prompts can narrow training coverage, whereas broader exploration can lower the fraction of informative prompts. To address these limitations, we introduce LEEPS, a Latent-Guided Explore--Exploit Prompt Sampler that adaptively balances the reuse of previously observed informative prompts with continued exploration of uncertain ones. LEEPS partitions candidates into exploit and explore portfolios and adaptively allocates rollout budget according to their recent non-trivial ratios. It further uses representation-space neighbors and historical rollout outcomes to prioritize uncertain prompts likely to yield non-zero reward variance, thereby making exploration more targeted without additional rollouts. Across six mathematical reasoning benchmarks, LEEPS achieves the highest average score at both model scales, with relative gains of 2.6% and 3.7% over the strongest baseline for Qwen2.5-Math-1.5B and 7B, respectively, and generally improves faster during the training process. It also achieves the highest average score across the three evaluated OOD general-reasoning benchmarks at both model scales and adds only about 2 seconds of online sampling overhead per training step. Code is available at https://github.com/ShuangLiangX/LEEPS.

Momentum

Related topics

Latest papers 168