The paper introduces ARLI, a latency‑aware framework that enables reinforcement learning fine‑tuning of large generalist robot policies despite inference delays. ARLI combines asynchronous inference with state augmentations—incorporating committed actions and mid‑inference observations—to restore near‑Markovian dynamics and maintain reactivity. Experiments on simulated and real‑world manipulation tasks show that ARLI allows effective policy improvement under latency, outperforming standard RL even in no‑latency scenarios.
By Brian Zhu (Siemens), Momen Khalil (Siemens), E Harrison (UC Berkeley), Emanuele Poggi (Siemens), Philipp Schmitt (Siemens), Bernd Kast (Siemens), Philine Meister (Siemens), Pranav Atreya (UC Berkeley), Qiyang Li (UC Berkeley), Finn Ferchau (Siemens), Cesar Colmenero (Siemens), Yash Shahapurkar (Siemens), Gokul Narayanan (Siemens), Melih Erdogan (Siemens), Kai Wurm (Siemens), Georg von Wichert (Siemens), Oier Mees (Microsoft, ETH Zurich, UC Berkeley), Eugen Solowjow (Siemens), Andrew Wagenmaker (UC Berkeley), Sergey Levine (UC Berkeley)
The paper proposes a deployment‑focused framework for deadline‑constrained network control, introducing the Effective Congestion (EC) metric family and Uniform Path Grouping (UPG) heuristic to better capture traffic urgency and balance load. It integrates these with a Multi‑Agent Deep Reinforcement Learning architecture (MADRL EC (p*)) that combines a distributed scheduler and a centralized RL router. A unified training objective merges live‑reward, pre‑collected‑reward, and policy‑imitation terms, leading to the Model‑Guided Annealed Reinforcement Learning (MGA‑RL) protocol built on DDPG, which generalizes offline‑to‑online learning for demonstration‑driven training.
By Vincenzo Norman Vitale, Mohammad Solki, Antonia Maria Tulino, Andreas F. Molisch, Jaime Llorca
arXiv:2606. 26463v1 Announce Type: new Abstract: Deliberating takes time.
By Aneesh Muppidi, Firas Darwish, Dylan Cope, Jo\~ao F. Henriques, Jakob Nicolaus Foerster
Deliberating takes time. In real-time settings, that time is not free.
arXiv:2607. 05064v1 Announce Type: new Abstract: Reinforcement learning in real world environments often suffers from severe performance degradation due to delayed feedback.
By Junqi Tu, Zejiao Liu, Fangfei Li, Yang Tang
arXiv:2603. 03480v2 Announce Type: replace Abstract: We study reinforcement learning with delayed state observation, where the agent observes the current state after some random number of time steps.
By Harin Lee, Kevin Jamieson
arXiv:2608. 11511v1 Announce Type: cross Abstract: In sequential decision making, an agent typically observes its environment and acts at every timestep.
By Christopher Watson, Arjun Krishna, Dinesh Jayaraman, Rajeev Alur
arXiv:2608.29562v1 Announce Type: new
Abstract: Ensuring the safe operation of multi-agent systems (MASs) under uncertain environments is crucial for cooperative robotic, where external disturbances...
By Xiaobing Dai, Zewen Yang, Wei Ren, Sandra Hirche
The paper proposes a new loss scheme that simultaneously supervises zeroth- and first-order actions to improve policy performance and control robustness in data-driven decision-making methods such as imitation learning and reinforcement learning. The approach provides formal theoretical guarantees, works with any off-the-shelf policy model, and can be added as a lightweight plug‑and‑play module to existing offline RL frameworks. Experiments on OGBench and D4RL show significant gains in performance, robustness, and out‑of‑distribution generalization, especially in low‑data settings.
By Peng Cheng, Yunxian Hou, Zhi Zhou, Qian Zhang, Chang Huang, Xianyuan Zhan
The paper presents Real‑Time EXPO‑FT, a reinforcement learning framework that fine‑tunes large Vision‑Language‑Action models for real‑time robotic control. It separates slow, expressive action generation from fast, reactive edits, allowing a lightweight policy to adjust actions based on the latest observation. Experiments on the Kinetix benchmark and four dynamic real‑world tasks show that Real‑Time EXPO‑FT achieves superior performance, improving policy success rates from 42% to 97% with only ten minutes of online data and no human intervention.
By Perry Dong, Kuo-Han Hung, Dorsa Sadigh, Chelsea Finn
arXiv:2607. 16421v1 Announce Type: new Abstract: It has long been recognized that humans have the ability to switch between fast, reactive decision-making and slower, deliberative planning.
By Adam Labiosa, Josiah P. Hanna
arXiv:2607. 07252v1 Announce Type: new Abstract: Reinforcement learning (RL) enables the synthesis of control policies directly from data, making it highly appealing for complex cyber-physical systems (CPSs) and robotics.
By Georg Sch\"afer, Jakob Rehrl, Stefan Huber, Simon Hirlaender