Tootfinder

Vier Raumfahrer von der ISS abgedockt
Rund eine Woche nach der Ankunft ihrer Ablöse-Crew haben sich vier Raumfahrer von der ISS auf den Weg zurück zur Erde gemacht.
https://www.heise.de/news/Vier-Raumfah…

Oil exploration in the Congo basin rainforest could be a disaster for nature and the climate https://www.theguardian.com/environment/2025/aug/07/opening-up-the-congo-basin-rainforest-could-be-a-disaster-for-na…

Analyse zur WWDC 2025-Keynote: Apple will (wieder) gut aussehen
Apple renoviert das Aussehen seiner Betriebssysteme und umgarnt die Entwickler. Aber wie stark sitzt dem iPhone-Hersteller das KI-Thema im Nacken? Eine Analyse.

Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library
Weixun Wang, Shaopan Xiong, Gengru Chen, Wei Gao, Sheng Guo, Yancheng He, Ju Huang, Jiaheng Liu, Zhendong Li, Xiaoyang Li, Zichen Liu, Haizhou Zhao, Dakai An, Lunxi Cao, Qiyang Cao, Wanxi Deng, Feilei Du, Yiliang Gu, Jiahe Li, Xiang Li, Mingjie Liu, Yijia Luo, Zihe Liu, Yadao Wang, Pei Wang, Tianyuan Wu, Yanan Wu, Yuheng Zhao, Shuaibing Zhao, Jin Yang, Siran Yang, Yingshui Tan, …

Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library
We introduce ROLL, an efficient, scalable, and user-friendly library designed for Reinforcement Learning Optimization for Large-scale Learning. ROLL caters to three primary user groups: tech pioneers aiming for cost-effective, fault-tolerant large-scale training, developers requiring flexible control over training workflows, and researchers seeking agile experimentation. ROLL is built upon several key modules to serve these user groups effectively. First, a single-controller architecture combin…

Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning
Ziyang Wang, Jaehong Yoon, Shoubin Yu, Md Mohaiminul Islam, Gedas Bertasius, Mohit Bansal
https://arxiv.org/abs/2507.06485

Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning
Despite advances in reinforcement learning (RL)-based video reasoning with large language models (LLMs), data collection and finetuning remain significant challenges. These methods often rely on large-scale supervised fine-tuning (SFT) with extensive video data and long Chain-of-Thought (CoT) annotations, making them costly and hard to scale. To address this, we present Video-RTS, a new approach to improve video reasoning capability with drastically improved data efficiency by combining data-ef…

Deep reinforcement learning for near-deterministic preparation of cubic- and quartic-phase gates in photonic quantum computing
Amanuel Anteneh L\'eandre Brunel, Carlos Gonz\'alez-Arciniegas, Olivier Pfister
https://arxiv.org/abs/2506.07859

Deep reinforcement learning for near-deterministic preparation of cubic- and quartic-phase gates in photonic quantum computing
Cubic-phase states are a sufficient resource for universal quantum computing over continuous variables. We present results from numerical experiments in which deep neural networks are trained via reinforcement learning to control a quantum optical circuit for generating cubic-phase states, with an average success rate of 96%. The only non-Gaussian resource required is photon-number-resolving measurements. We also show that the exact same resources enable the direct generation of a quartic-phase…

Improving Long-Range Navigation with Spatially-Enhanced Recurrent Memory via End-to-End Reinforcement Learning
Fan Yang, Per Frivik, David Hoeller, Chen Wang, Cesar Cadena, Marco Hutter
https://arxiv.org/abs/2506.05997

Improving Long-Range Navigation with Spatially-Enhanced Recurrent Memory via End-to-End Reinforcement Learning
Recent advancements in robot navigation, especially with end-to-end learning approaches like reinforcement learning (RL), have shown remarkable efficiency and effectiveness. Yet, successful navigation still relies on two key capabilities: mapping and planning, whether explicit or implicit. Classical approaches use explicit mapping pipelines to register ego-centric observations into a coherent map frame for the planner. In contrast, end-to-end learning achieves this implicitly, often through rec…

Reinforcement Learning for Trade Execution with Market Impact
Patrick Cheridito, Moritz Weiss
https://arxiv.org/abs/2507.06345 https://

Reinforcement Learning for Trade Execution with Market Impact
In this paper, we introduce a novel reinforcement learning framework for optimal trade execution in a limit order book. We formulate the trade execution problem as a dynamic allocation task whose objective is the optimal placement of market and limit orders to maximize expected revenue. By employing multivariate logistic-normal distributions to model random allocations, the framework enables efficient training of the reinforcement learning algorithm. Numerical experiments show that the proposed…

Die Stimme von "Houston, we´ve had a problem" ist verstummt
Mit 97 Jahren ist NASA-Astronaut Jim Lovell gestorben. Seine Raumfahrt-Karriere ist eine Geschichte des Scheiterns und Weitermachens – und von viel Glück.

Detecting and Mitigating Reward Hacking in Reinforcement Learning Systems: A Comprehensive Empirical Study
Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma
https://arxiv.org/abs/2507.05619

Detecting and Mitigating Reward Hacking in Reinforcement Learning Systems: A Comprehensive Empirical Study
Reward hacking in Reinforcement Learning (RL) systems poses a critical threat to the deployment of autonomous agents, where agents exploit flaws in reward functions to achieve high scores without fulfilling intended objectives. Despite growing awareness of this problem, systematic detection and mitigation approaches remain limited. This paper presents a large-scale empirical study of reward hacking across diverse RL environments and algorithms. We analyze 15,247 training episodes across 15 RL e…