RLinf-USER: A Unified and Extensible System for Real-World Online Policy Learning in Embodied AI

• URL: http://arxiv.org/abs/2602.07837v3
• Date: Thu, 12 Feb 2026 08:08:43 GMT
• Title: RLinf-USER: A Unified and Extensible System for Real-World Online Policy Learning in Embodied AI
• Abstract summary: We present USER, a Unified and SystEm for Real-world online policy learning.<n>We show that USER enables multi-robot coordination, heterogeneous manipulators, edge-cloud collaboration with large models, and long-running asynchronous training.<n>Results in both simulation and the real world show that USER enables online imitation or reinforcement learning of CNN/MLP, generative policies, and large vision-action (VLA) models within a unified pipeline.
• Score: 44.06975079994439
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Online policy learning directly in the physical world is a promising yet challenging direction for embodied intelligence. Unlike simulation, real-world systems cannot be arbitrarily accelerated, cheaply reset, or massively replicated, which makes scalable data collection, heterogeneous deployment, and long-horizon effective training difficult. These challenges suggest that real-world policy learning is not only an algorithmic issue but fundamentally a systems problem. We present USER, a Unified and extensible SystEm for Real-world online policy learning. USER treats physical robots as first-class hardware resources alongside GPUs through a unified hardware abstraction layer, enabling automatic discovery, management, and scheduling of heterogeneous robots. To address cloud-edge communication, USER introduces an adaptive communication plane with tunneling-based networking, distributed data channels for traffic localization, and streaming-multiprocessor-aware weight synchronization to regulate GPU-side overhead. On top of this infrastructure, USER organizes learning as a fully asynchronous framework with a persistent, cache-aware buffer, enabling efficient long-horizon experiments with robust crash recovery and reuse of historical data. In addition, USER provides extensible abstractions for rewards, algorithms, and policies, supporting online imitation or reinforcement learning of CNN/MLP, generative policies, and large vision-language-action (VLA) models within a unified pipeline. Results in both simulation and the real world show that USER enables multi-robot coordination, heterogeneous manipulators, edge-cloud collaboration with large models, and long-running asynchronous training, offering a unified and extensible systems foundation for real-world online policy learning.

Related papers

• FluxVLA Engine: A One-Stop VLA Engineering Platform for Embodied Intelligence [21.911710953682256]
  $mathrmFluxVLA$ is an open, configuration-driven platform that turns heterogeneous embodied-policy components into a data-to-deployment workflow.<n>$mathrmFluxVLA$ standardizes interfaces for datasets, visual-language and world models, action heads, reward- or advantage-weighted learning, distributed training, simulation evaluation, optimized inference, and robot operators.
  arXiv  Detail & Related papers  (2026-09-15T13:59:09Z)
• End-to-end example-based sim-to-real RL policy transfer based on neural stylisation with application to robotic cutting [3.398964351541323]
  We propose a novel method for sim-to-real transfer of reinforcement learning policies.<n>We employ a variational autoencoder to jointly learn self-supervised feature representations for style transfer.<n>We demonstrate the application of our approach based on the case study of robot cutting of unknown materials.
  arXiv  Detail & Related papers  (2026-01-28T18:45:55Z)
• SOP: A Scalable Online Post-Training System for Vision-Language-Action Models [15.86316960521611]
  Vision-language-action (VLA) models achieve strong generalization through large-scale pre-training, but real-world deployment requires expert-level task proficiency in addition to broad generality.<n>Existing post-training approaches for VLA models are typically offline, single-robot, or task-specific.<n>We introduce a Scalable Online Post-training system that enables online, distributed, multi-task post-training of generalist VLA models directly in the physical world.
  arXiv  Detail & Related papers  (2026-01-06T14:25:11Z)
• Federated Learning Framework for Scalable AI in Heterogeneous HPC and Cloud Environments [0.1805840413757548]
  We present a federated learning framework built to run efficiently across mixed HPC and cloud environments.<n>Our system addresses key challenges such as system het- erogeneity, communication overhead, and resource scheduling, while maintaining model accuracy and data privacy.
  arXiv  Detail & Related papers  (2025-11-22T18:39:25Z)
• Watch and Learn: Learning to Use Computers from Online Videos [50.10702690339142]
  Watch & Learn (W&L) is a framework that converts human demonstration videos readily available on the Internet into executable UI trajectories at scale.<n>We develop an inverse dynamics labeling pipeline with task-aware video retrieval, generate over 53k high-quality trajectories from raw web videos.<n>These results highlight web-scale human demonstration videos as a practical and scalable foundation for advancing CUAs towards real-world deployment.
  arXiv  Detail & Related papers  (2025-10-06T10:29:00Z)
• A General Infrastructure and Workflow for Quadrotor Deep Reinforcement Learning and Reality Deployment [48.90852123901697]
  We propose a platform that enables seamless transfer of end-to-end deep reinforcement learning (DRL) policies to quadrotors.<n>Our platform provides rich types of environments including hovering, dynamic obstacle avoidance, trajectory tracking, balloon hitting, and planning in unknown environments.
  arXiv  Detail & Related papers  (2025-04-21T14:25:23Z)
• Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics [50.191655141020505]
  This work advances model-based reinforcement learning by addressing the challenges of long-horizon prediction, error accumulation, and sim-to-real transfer.<n>By providing a scalable and robust framework, the introduced methods pave the way for adaptive and efficient robotic systems in real-world applications.
  arXiv  Detail & Related papers  (2025-01-17T10:39:09Z)
• RIS-empowered Topology Control for Distributed Learning in Urban Air Mobility [35.04722426910211]
  Urban Air Mobility (UAM) expands vehicles from the ground to the near-ground space, envisioned as a revolution in transportation systems. To overcome the challenge, federated learning (FL) and other collaborative learning have been proposed to enable resource-limited devices to conduct onboard deep learning (DL) collaboratively. This paper explores reconfigurable intelligent surfaces (RIS) empowered distributed learning, taking account of topological attributes to facilitate the learning performance with convergence guarantee.
  arXiv  Detail & Related papers  (2024-03-08T08:05:50Z)
• Benchmarking Offline Reinforcement Learning on Real-Robot Hardware [35.29390454207064]
  Dexterous manipulation in particular remains an open problem in its general form. We propose a benchmark including a large collection of data for offline learning from a dexterous manipulation platform on two tasks. We evaluate prominent open-sourced offline reinforcement learning algorithms on the datasets and provide a reproducible experimental setup for offline reinforcement learning on real systems.
  arXiv  Detail & Related papers  (2023-07-28T17:29:49Z)
• Cloud-Edge Training Architecture for Sim-to-Real Deep Reinforcement Learning [0.8399688944263843]
  Deep reinforcement learning (DRL) is a promising approach to solve complex control tasks by learning policies through interactions with the environment. Sim-to-real approaches leverage simulations to pretrain DRL policies and then deploy them in the real world. This work proposes a distributed cloud-edge architecture to train DRL agents in the real world in real-time.
  arXiv  Detail & Related papers  (2022-03-04T10:27:01Z)
• SOLIS -- The MLOps journey from data acquisition to actionable insights [62.997667081978825]
  In this paper we present a unified deployment pipeline and freedom-to-operate approach that supports all requirements while using basic cross-platform tensor framework and script language engines. This approach however does not supply the needed procedures and pipelines for the actual deployment of machine learning capabilities in real production grade systems.
  arXiv  Detail & Related papers  (2021-12-22T14:45:37Z)
• Deep Learning for Ultra-Reliable and Low-Latency Communications in 6G Networks [84.2155885234293]
  We first summarize how to apply data-driven supervised deep learning and deep reinforcement learning in URLLC. To address these open problems, we develop a multi-level architecture that enables device intelligence, edge intelligence, and cloud intelligence for URLLC.
  arXiv  Detail & Related papers  (2020-02-22T14:38:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.