Reinforcement Learning

Also known as RL

Follow this topic Ask about this topic

Momentum

144 papers in the last four weeks, up 243% on the four weeks before. 1.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 1,138

All topics

Beyond Pixels: Learning Invariant Rewards for Real-World Robotics From a Few Demonstrations
May 21, 2026Tengye Xu, Yangting Sun, Ziju Shen +5Reinforcement Learning Generalization in Robotic Manipulation
School of Computing and Data Science, The University of Hong Kong · 2LimX Dynamics Technology Co., Ltd · 4Peking University +2
On the Sample Complexity of Discounted Reinforcement Learning with Optimized Certainty Equivalents
May 20, 2026Oliver Mortensen, Mohammad Sadegh TalebiReinforcement Learning Risk-Sensitive RL
Department of Computer Science, University of Copenhagen.
Value-Gradient Hypothesis of RL for LLMs
May 20, 2026Arip Asadulaev, Daniil Ognev, Karim Salta +1RL for Language Models Policy Gradient
MBZUAI · Independent
Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent
May 20, 2026Zeyuan Wang, Da Li, Yulin Chen +6Reinforcement Learning Maximum Entropy RL
Laboratory for Big Data and Decision, National University of Defense Technology, China · Samsung AI Center Cambridge, UK · Queen Mary University of London, UK +3
Behavior-Consistent Deep Reinforcement Learning
May 20, 2026Marcel Hussing, Liv G. d'Aliberti, Claas Voelcker +2Reinforcement Learning Policy Optimization
University of Pennsylvania · Princeton University · University of Texas at Austin
Domain-Adaptable Reinforcement Learning for Code Generation with Dense Rewards
May 20, 2026Erfan Aghadavoodi Jolfaei, Daniel Maninger, Abhinav Anand +2RL for Code Generation Reinforcement Learning
Technische Universität Darmstadt, Darmstadt, Germany · Hessian Center for Artificial Intelligence (hessian.AI), Darmstadt, Germany · National Research Center for Applied Cybersecurity ATHENE, Darmstadt, Germany.
Scalable Reinforcement Learning via Adaptive Batch Scaling
May 20, 2026Jongchan ParkNon-Stationary RL Reinforcement Learning
Hyundai Motor Company
Beyond the Bellman Recursion: A Pontryagin-Guided Framework for Non-Exponential Discounting
May 20, 2026Hojin Ko, Jeonggyu HuhReinforcement Learning Stochastic Optimal Control
Department of Mathematics, Sungkyunkwan University, Suwon, Republic of Korea
For How Long Should We Be Punching? Learning Action Duration in Fighting Games
May 20, 2026Hoang Hai Nguyen, Kurt Driessens, Dennis J. N. J. SoemersReinforcement Learning Game-Playing Agents
Department of Advanced Computing Sciences, Maastricht University, Maastricht, the Netherlands
Compositional Transduction with Latent Analogies for Offline Goal-Conditioned Reinforcement Learning
May 20, 2026Junseok Kim, Dohyeong Kim, Mineui Hong +1Reinforcement Learning Robotic RL
Department of Electrical and Computer Engineering and ASRI, Seoul National University · Independent researcher · Robotics Institute, Carnegie Mellon University
ReversedQ: Opportunities for Faster Q-Learning in Episodic Online Reinforcement Learning
May 20, 2026Sofia R. Miskala-Dinc, Aviva PrinsReinforcement Learning Q-Learning
University of Maryland College Park, MD, United States
Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents
May 19, 2026Wenjie Tang, Minne Li, Sijie Huang +2Reinforcement Learning Partially Observable RL
College of Computer, National University of Defense Technology · 2Intelligent Game and Decision Lab (IGDL) · Institute of Artificial Intelligence, Xiamen University
A conceptual framework for learning to listen by reward: Curiosity-driven search for novel sources
May 19, 2026Andreas Triantafyllopoulos, Jakub Šťastný, Alexios Terpinas +3Reinforcement Learning Intrinsic Motivation
CHI – Chair of Health Informatics, Technical University of Munich, Munich, Germany · MCML – Munich Center for Machine Learning, Munich, Germany · MDSI – Munich Data Science Institute, Munich, Germany +1
Beyond Action Residuals: Real-World Robot Policy Steering via Bottleneck Latent Reinforcement Learning
May 19, 2026Dongjie Yu, Kun Lei, Zhennan Jiang +2Robot Policy Adaptation Reinforcement Learning
School of Computing and Data Science, The University of Hong Kong, Hong Kong SAR. · Shanghai Qizhi Institute, Shanghai, China. · Shanghai Jiao Tong University, Shanghai, China. +2
Minimax Optimal Variance-Aware Regret Bounds for Multinomial Logistic MDPs
May 19, 2026Pierre Boudart, Pierre Gaillard, Alessandro RudiRegret Minimization in RL Markov Decision Processes
SIERRA · INRIA, École Normale Supérieure CNRS, PSL Research University Paris, France · Thoth +3
GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment
May 19, 2026Minxuan Lv, Tiehua Mei, Tanlong Du +9Reinforcement Learning Long-Context Modeling
Kuaishou Technology · University of Chinese Academy of Sciences
What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents
May 19, 2026Xiaozhe Li, Tianyi Lyu, Yang Li +6Reinforcement Learning Credit Assignment in RL
1Tongji University · 2Shanghai AI Laboratory · 5Independent +2
Detecting and Mitigating the Correct-Answer Extinction Window in Test-Time Reinforcement Learning with Majority Voting
May 19, 2026Hongxiang Lin, Zhirui Kuai, Erpeng Xue +1Reinforcement Learning RL for Language Model Reasoning
Meituan
GAE Falls Short in Imperfect-Information Self-Play Reinforcement Learning
May 19, 2026Zhiyuan Fan, Gabriele FarinaReinforcement Learning Self-Play RL
MIT
Precision Physical Activity Prescription via Reinforcement Learning for Functional Actions
May 19, 2026Gefei Lin, Rui Miao, Jennifer Sacheck +1Reinforcement Learning Offline RL
Department of Statistics, The George Washington University · Department of Mathematical Sciences, The University of Texas at Dallas · Department of Behavioral and Social Sciences, Brown University
A Heuristic Approach for Performance Tuning in RL-based Quadrotor Control via Reward Design and Termination Conditions
May 18, 2026Fausto Mauricio Lagos Suarez, Akshit Saradagi, Vidya Sumathy +1RL Control Robot Trajectory Tracking
Robotics and AI group, in the Department of Computer Science, Electrical and Space Engineering at Luleåa University of Technology, Sweden
AMARIS: A Memory-Augmented Rubric Improvement System for Rubric-Based Reinforcement Learning
May 18, 2026Peilin Wu, Xinlu Zhang, Kun Wan +4RL for Language Models Reinforcement Learning
The University of Texas at Dallas · Department of Computer Science, University of California, Santa Barbara · Adobe Inc.
DiPRL: Learning Discrete Programmatic Policies via Architecture Entropy Regularization
May 18, 2026Chengpeng Hu, Yingqian Zhang, Hendrik BaierReinforcement Learning Program Synthesis
Eindhoven University of Technology, Eindhoven, the Netherlands · Centrum Wiskunde & Informatica, Amsterdam, the Netherlands
Scheduling That Speaks: An Interpretable Programmatic Reinforcement Learning Framework
May 18, 2026Chengpeng Hu, Yingqian Zhang, Hendrik BaierReinforcement Learning Interpretable ML
Eindhoven University of Technology, Eindhoven, the Netherlands · Centrum Wiskunde & Informatica, Amsterdam, the Netherlands
PH-Dreamer: A Physics-Driven World Model via Port-Hamiltonian Generative Dynamics
May 18, 2026Xueyu Luan, Chenwei ShiDynamical Systems Reinforcement Learning
School of Electronic and Information Engineering Tongji University Shanghai 200092, China · Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai 200092, China
Privacy Preserving Reinforcement Learning with One-Sided Feedback
May 18, 2026Lin William Cong, Guangyan Gan, Hanzhang Qin +1Reinforcement Learning Partially Observable RL
1Nanyang Technological University · Cornell SC Johnson College of Business · 2National University of Singapore
RL4RLA: Teaching ML to Discover Randomized Linear Algebra Algorithms Through Curriculum Design and Graph-Based Search
May 18, 2026Jinglong Xiong, Xiaotian Liu, Ruoxin Wang +4Reinforcement Learning Automated Algorithm Discovery
Pratt School of Engineering, Duke University, Durham, NC, USA · Department of Computer Science, Dartmouth College, Hanover, NH, USA.
Enhancing the Code Reasoning Capabilities of LLMs via Consistency-based Reinforcement Learning
May 18, 2026Zhanyue Qin, Jia Feng, Yibo Lyu +4Reinforcement Learning RL for Language Model Reasoning
Harbin Institute of Technology · The Chinese University of Hong Kong
GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents
May 18, 2026Xiongbin Wu, Zhihao Luo, Shanzhe Lei +7Reinforcement Learning Group Relative Policy Optimization
Shanghai Jiao Tong University · Shanghai Artificial Intelligence Laboratory · East China Normal University +2
HydroAgent: Closing the Gap Between Frontier LLMs and Human Experts in Hydrologic Model Calibration via Simulator-Grounded RL
May 18, 2026Zhi Li, Songkun Yan, Jie Cao +4Reinforcement Learning Model Calibration
Civil, Environmental, and Architectural Engineering, University of Colorado Boulder · Civil Engineering and Environmental Sciences, University of Oklahoma · Department of Computer Science, University of Oklahoma +3

May 21, 2026, cs.ROJ/K move · Enter open · S save

Beyond Pixels: Learning Invariant Rewards for Real-World Robotics From a Few Demonstrations

Tengye Xu, Yangting Sun, Ziju Shen, Guanqi Chen+4

School of Computing and Data Science, The University of Hong Kong · 2LimX Dynamics Technology Co., Ltd · 4Peking University+2

Reinforcement Learning Generalization in Robotic Manipulation Robotic Manipulation Robot Policy Generalization

Open paper AskPDF arXiv

Designing reward functions that generalize beyond controlled laboratory settings remains a fundamental challenge in reinforcement learning for robotics. In open-world manipulation problems, a single task can appear in numerous variants through different object instances, positions, and camera viewpoints. Recent vision-based reward models tend to memorize specific pixel distributions and fail to generalize beyond their training conditions. To address this, we propose a framework that learns invariant symbolic reward functions from as few as five demonstrations. The insight is to shift from visual feature-fitting to the discovery of behavioral invariants: task-level properties that remain constant across diverse visual instantiations. The framework has two coupled components: a structural reward formulation that encodes task-level strategies and physical constraints while preserving optimal policy invariance, and a hybrid symbolic-numerical procedure that distills these invariants from demonstrations without online interaction. Experiments on eight Meta-World tasks and three Franka manipulation tasks demonstrate that our method achieves stronger process alignment and policy rollout ranking abilities compared to baselines, accelerating downstream policy learning. Three real-world out-of-distribution experiments further show that the same learned reward generalizes zero-shot to position, viewpoint, and object variations, enabling a single reward representation to be reused across diverse task variants in practice.

Momentum

Related topics

Latest papers 1,138