Robotic RL

RL: Reinforcement Learning

Follow this topic Ask about this topic

Momentum

28 papers in the last four weeks, up 180% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 184

All topics

A Balanced Data Diet: Addressing the Exploration Bottleneck in Mega-Scale RL for Robot Control
Oct 8, 2026Octi Zhang, Mateo Guaman Castro, Patrick Yin +4Robotic RL Data-Efficient Robot Learning
University of Washington · NVIDIA
Leveraging Human-In-The-Loop Demonstrations in Reinforcement Learning for Digital Twin-Driven Robot Flexibility
Oct 8, 2026Yuzhu Sun, Mien Van, Nguyen Minh Nhat +2Robotic RL Human-in-the-Loop AI
School of Electronics, Electrical Engineering and Computer Science, Queen’s University Belfast, Northern Ireland, UK
Reliability-Aware Future Conditioning for Temporally Robust Robot Manipulation
Oct 8, 2026Mohammad Khoshnazar, Mohammad Dehghani Tezerjani, Zhiyuan Gao +8Robotic Manipulation Robotic RL
University of Bremen, Bremen, Germany · University of North Texas, Denton, TX, USA · Toyota Motor North America, Mountain View, CA, USA
FOCUS: From Privileged States to RGB-D with Controlled Modality Switching and Representation Alignment
Oct 8, 2026Filip Grigorov, Kourosh Darvish, Nandita VijaykumarRobotic RL Visual RL
University of Toronto Canada
QF3: Fast Flow RL with Filtered Q-Gradients
Oct 6, 2026Chung Min Kim, Brent Yi, David McAllister +7Robotic RL RL for Legged Locomotion
UC Berkeley · Amazon FAR
PEARS: Physical-Prior-Guided Efficient Adaptation via Failure Reasoning and Diffusion Steering for Tactile Manipulation
Oct 6, 2026Kun Song, Yiming Wang, Yilin Chen +5Robot Policy Adaptation Robotic RL
The University of Hong Kong · Shanghai Jiao Tong University · Xense Robotics +1
Revisiting Temporal Regularization for Smooth Control in Deep Reinforcement Learning
Oct 6, 2026SungJae Ahn, Jeong Woon Lee, Kyoleen Kwak +1RL Control Reinforcement Learning
College of Software, Kyung Hee University.
Learning Grasp Targeting from Point Clouds for Log Pile Clearing on a Hydraulic Crane
Oct 6, 2026George Sideris, Lucas Bessai, Heshan Fernando +3Robotic Grasping Sim-to-Real Transfer
McGill University, Montreal, QC, Canada. · FPInnovations, Pointe-Claire, QC, Canada.
End-to-End Safe Social Navigation via Multi-Task Reinforcement Learning and Probabilistic Perception
Oct 5, 2026Tommaso Van Der Meer, Andrea Garulli, Antonio Giannitrapani +3Robotic RL Safe Robot Navigation
Dipartimento di Ingegneria dell’Informazione e Scienze Matematiche, Universit`a di Siena, Siena, Italy · Uninettuno University, Rome, Italy · Visual Intelligence for Transportation (VITA) Lab, ´Ecole Polytechnique F´ed´erale de Lausanne (EPFL), Lausanne, Switzerland
Tactile Curiosity Drives Robot Interaction
Sep 30, 2026Klemens Iten, Alexander Proshkin, Bhavya Sukhija +4Robotic RL Data-Efficient Robot Learning
University of California, Berkeley United States · The University of Texas at Austin United States
Linear Recurrent Memory Suffices to Distil a World-Model Policy for Robot Air Hockey
Sep 30, 2026F. Olivia Fan, Oliver ObstRecurrent Neural Networks Robotic RL
UNSW Sydney, NSW 2052, Australia
PRICE the Action Chunks: Physical Relational Credit Assignment for Embodied Reinforcement Learning
Sep 30, 2026Yangang Zou, Jiajun Lu, Weitao Zhou +6Credit Assignment in RL Step-Level Credit Assignment in RL
School of Data Science, Fudan University · Shanghai Innovation Institute · Beihang University +4
Action Chunking Proximal Policy Optimization with Feedback Correction
Sep 28, 2026Sanghyun Hahn, Jonghyun ChoiRobotic RL Feedback Control
Cornell University · Seoul National University
F4R: Failure-Driven Recognition, Reconstruction, Refinement, and Redeployment for Continual Robot Self-Improvement
Sep 28, 2026Zhuoyuan Yu, Jiacheng Wang, Tianle Liu +13Continual Robot Learning Sim-to-Real Transfer
Nanyang Technological University · Xi’an Jiaotong University · Dexmal
Sufficiency of Zeroth-Order Reward Shaping for Policy Gradient in Stabilization Control
Sep 28, 2026Yisheng Zhang, Tao Wang, Sicun GaoReward Shaping Robotic RL
University of California San Diego, La Jolla, CA, USA · Tsinghua University, Beijing, China
ZeroBot: Learning from Scratch in Minutes with Generative Real2Sim
Sep 27, 2026Ivan Kapelyukh, Xiaohan Zhang, Stephen James +2Robotic RL Robotic Manipulation
Imperial College London · Robotics and AI Institute
Demonstration-Free Success-Probability Reward Learning for Generalist Robot Policies
Sep 27, 2026Duo Wu, Haifeng Wang, Rongwei Lu +6Robotic RL Sparse-Reward RL
Tsinghua University · Yuanxing Robotics · Pengcheng Laboratory
Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning
Sep 24, 2026Sudip Bhujel, Shanghao Shi, Ruiquan Huang +2Gradient Inversion Attacks Robotic RL
Department of Computer Science, University of Kentucky · Department of Computer Science and Engineering, Washington University in St. Louis
Simple Torque-Observation Alignment for Zero-Shot Sim-to-Real Grasping with a Direct-Drive Gripper
Sep 24, 2026Doyoung Kim, Edgar Lee, Hyeonsun Park +4Robotic Grasping Sim-to-Real Transfer
Department of Mechanical Engineering, Sogang University, Seoul, South Korea
EBRL: Asynchronous Embodied RL by Multi-Grained Resource Management
Sep 23, 2026Liang Mi, Weijun Wang, Bowen Gao +12Asynchronous RL Reinforcement Learning
Nanjing University · Institute for AI Industry Research (AIR), Tsinghua University · Nanjing University of Posts and Telecommunications +1
Learning to Plan in Human-Robot Collaboration: Multimodal Reinforcement Learning for Adaptive Interaction
Sep 21, 2026Afagh Mehri Shervedani, Siyu Li, Natawut Monaikul +3Reinforcement Learning Robotic RL
University of Illinois Chicago, Chicago, IL 60607 USA · California State University Channel Islands
Performance-Preserving Online Adaptation in Social Navigation via Diffusion Steering
Sep 21, 2026Haruto Nagahisa, Kohei Matsumoto, Yuki Hyodo +1Robot Policy Adaptation Reinforcement Learning
Graduate School of Information Science and Electrical Engineering, Kyushu University, Fukuoka, Japan · Faculty of Information Science and Electrical Engineering, Kyushu University, Fukuoka, Japan
PINGU: Extending Air-Bearing Spacecraft Emulators with Open-Source Actuators and Learned Control for Contact-Rich Proximity Operations
Sep 20, 2026Ricard Marsal I Castan, Akiyoshi Uchida, Aman Arora +7Space Robotics Contact-Rich Robotic Manipulation
University of Luxembourg · Tohoku University · Georgia Institute of Technology
SeeQ: Training Generalist Value Functions for Long-Horizon Robotic Manipulation
Sep 18, 2026Saksham Singh, Zheyuan Hu, Max Sobol Mark +3Robot Policy Learning Long-Horizon Robotic Manipulation
Carnegie Mellon University
From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention
Sep 18, 2026Sichang Su, Benjamin Yang, Zhiyun Deng +4Robot Policy Adaptation Reinforcement Learning
UT Austin · Autel US · UC Berkeley
Hybrid Residual Reinforcement Learning for Contact-Rich Robotic Book Insertion
Sep 17, 2026Tianyuan Liu, Rutherford Agbeshi Patamia, Benjamin Champion +2Contact-Rich Robotic Manipulation Robotic RL
Deakin University, Australia
GR2PO: Group Relative Return Policy Optimization for Continuous Robot Control
Sep 17, 2026Pengqin Wang, Qiming Zhang, Shaojie Shen +1Reinforcement Learning Group Relative Policy Optimization
Robotics and Autonomous Systems Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · Division of Emerging Interdisciplinary Areas, the Hong Kong University of Science and Technology, Hong Kong SAR, China · Intelligent Transportation Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China +1
EmbodiedMind: Adaptive Data Curation and Prefix-Tree Reinforcement Learning for Efficient Embodied Intelligence
Sep 17, 2026Feifan Wang, Zongbing Zhang, Yu Zhang +8Reinforcement Learning Robot Foundation Models
ZTE Corporation, Shenzhen, China
WeaveRL: Weaving Reconstruction into Scene-Aware Fabrics for Perceptive Reinforcement Learning
Sep 16, 2026Remo Steiner, Vikram Ramasamy, David Tingdahl +73D Reconstruction Generalization in Robotic Manipulation
NVIDIA Corporation. Zurich, Seattle and Santa Clara.
FIERCE: From Generalist Robot Policies to Fast Specialists via Progress-Failure Feedback
Sep 16, 2026Runjia Tan, Yuang Tu, Yujie Yan +3Reward Modeling Robot Policy Learning
Nanyang Technological University. · Guangzhou Cloudbutterfly Technology Co., Ltd.

Oct 8, 2026, cs.ROJ/K move · Enter open · S save

A Balanced Data Diet: Addressing the Exploration Bottleneck in Mega-Scale RL for Robot Control

Octi Zhang, Mateo Guaman Castro, Patrick Yin, Ignacio Dagnino+3

University of Washington · NVIDIA

Robotic RL Data-Efficient Robot Learning RL for Legged Locomotion

Open paper AskPDF arXiv

General-purpose robots must perform a wide range of tasks from agile locomotion to dexterous manipulation. While sim-to-real reinforcement learning (RL) has proven to be a useful tool for this goal, current RL pipelines depend on engineering-heavy, per-task structural priors such as shaped rewards and demonstrations. Recent work has shown that diverse simulator resets, combined with massively parallel simulation, can alleviate much of this engineering burden on several manipulation problems. However, we find that naively scaling this paradigm to more precise or dynamic problems remains non-trivial. While simulator resets can help with exploration, uniformly sampling over this distribution wastes a growing fraction of learning experience on task configurations the policy has already mastered or cannot yet attempt. This makes it challenging to see the expected benefits of scaling parallel environments for RL, since much of the learning signal in a batch is wasted during learning. To mitigate this, we introduce Success Guided Sampling (SGS), a simple adaptive sampler that concentrates RL training on task configurations around the frontier of the policy's capabilities. Doing so allows large-scale simulated RL to make the most out of the experience in a batch, enabling much more effective scaling to large-scale parallel simulation. Across experiments using up to

2^{20}

(over one million) parallel environments, SGS enables RL to solve challenging multi-terrain quadruped locomotion and contact-rich assembly tasks that prior methods fail to solve. Finally, we distill the learned manipulation policies into RGB-based policies and demonstrate zero-shot transfer to several challenging assembly tasks on real hardware. Project website: https://sgs-rl.github.io/.

Momentum

Related topics

Latest papers 184