arXiv Machine Learning September 22, 2026 By Julian Oelhaf, Alexander Luce, Christian Bergler, Andreas Maier, Siming Bayer

Offline Reinforcement Learning for Distribution-Grid Protection

Read the original on arXiv Machine Learning →

The paper investigates using offline reinforcement learning to improve line‑selective tripping in distribution grids. A convolutional Q‑network trained with conservative Q‑learning (CQL) processes voltage‑current phasor and impedance data, optionally with raw waveforms, to predict faulted lines. On a realistic CIGRE medium‑voltage network, the best model achieved high per‑timestep precision, recall, and F1‑score, and correctly identified the first trip action in over 98% of fault episodes, though it mis‑tripped in a notable fraction of non‑fault cases.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 8

Federated Physics-Grounded Reinforcement Learning for Distributed Stability Control in Smart Grids

arXiv:2607. 05553v1 Announce Type: new Abstract: Transient stability control in smart grids requires rapid post-fault damping of generator frequency and rotor angle deviations to prevent cascading failures.

By Omar Al-Refai, Ibrahim Shahbaz, Adam Ali Husseinat, Eman Hammad

agents reinforcement-learning efficiency benchmarks

arXiv AI

Jun 30

Pessimism's Paradox: Conservative Offline Training Amplifies Reward Hacking During Online Adaptation in Reasoning Models

arXiv:2606. 30627v1 Announce Type: cross Abstract: Conservative offline training is widely advocated as a safe foundation for subsequent online adaptation: if a policy stays close to well-supported behaviour, the argument goes, it is less likely to exploit imperfections in a learned reward model.

By Subramanyam Sahoo, Aman Chadha, Vinija Jain, Divya Chaudhary

reinforcement-learning safety

arXiv AI

Jun 3

When RLHF Fails: A Mechanistic Taxonomy of Reward Hacking, Collapse, and Evaluator Gaming

arXiv:2606. 03238v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) makes large-scale post-training possible by replacing an underspecified human objective with learned and scalable proxies.

By Zelalem Abahana

llms reinforcement-learning safety

arXiv AI

Jun 15

Safety-Contract Graph Multi-Agent Reinforcement Learning for Autonomous Network Security Response

arXiv:2606. 13832v1 Announce Type: cross Abstract: Autonomous network-security response systems promise to reduce Security Operations Centre (SOC) reaction latency, but reward-only multi-agent reinforcement learning (MARL) can improve security reward while remaining non-deployable.

By Jose Luis Lima de Jesus Silva

agents reinforcement-learning benchmarks safety

arXiv Machine Learning

Jul 14

Q-Learning Lab: Teaching Reinforcement Learning Through Learner-Generated Trace Analysis

arXiv:2607. 10802v1 Announce Type: cross Abstract: Reinforcement learning is usually introduced through the Bellman update, yet the equation often remains abstract to undergraduates: they watch policy arrows converge but rarely observe how each value is computed or why an action is chosen.

By Ekkachai Jueng

agents reinforcement-learning

arXiv AI

Aug 25

Let Credit Follow Computation: Architecture-Aware Credit Transport for Large Language Model Reinforcement Learning

arXiv:2608.21501v1 Announce Type: new Abstract: Credit assignment in large-language-model reinforcement learning (LLM RL) can be separated into three objects: evidence about success, a transport oper...

By Qifan Shi, Zhaolu Kang, Chenghua Zhu

llms reinforcement-learning safety

One email a morning, machine-written

Related stories

Federated Physics-Grounded Reinforcement Learning for Distributed Stability Control in Smart Grids

Pessimism's Paradox: Conservative Offline Training Amplifies Reward Hacking During Online Adaptation in Reasoning Models

When RLHF Fails: A Mechanistic Taxonomy of Reward Hacking, Collapse, and Evaluator Gaming

Safety-Contract Graph Multi-Agent Reinforcement Learning for Autonomous Network Security Response

Q-Learning Lab: Teaching Reinforcement Learning Through Learner-Generated Trace Analysis

Let Credit Follow Computation: Architecture-Aware Credit Transport for Large Language Model Reinforcement Learning