Category
2,073 papers
We identify a structured confound in Reinforcement Learning from Human Feedback (RLHF). Pairwise preference labels are intended to reflect the compared outputs. They may also reflect the rater's state during annotation. Under sustained stressful or distressing conditions, a rater's preferences may shift over time, so t...
Large Language Models (LLMs) have demonstrated remarkable fluency across many tasks but remain limited by their static, parameter-bound knowledge and their susceptibility to hallucinating information. Retrieval-Augmented Generation (RAG) addresses these issues by incorporating external retrieval into the generation pro...
The article argues that many contemporary AI alignment practices risk a mistaken assimilation of moral agency to statistical learning. Techniques such as reinforcement learning from human feedback and constitutional AI often treat morality as a behavioral function that can be approximated from human discourse, behavior...
Software Vulnerability (SV) assessment is a vital phase in SV management, which characterizes discovered SVs to locate hot spots and prioritize their remediation. To reduce the overhead and latency of manual assessment, prior works have explored automatically predicting assessment results from SV reports (SVRs). Howeve...
Reach audiences
Advertise in front of researchers, engineers, and readers.
This study proposes a deep reinforcement learning framework for bridge maintenance decision-making and indicates that Prioritized experience replay (PER) Deep Q-Networks (DQN) fits engineering data samples well and shows stronger cost-reduction performance than Double DQN.
The modern bio-medical systems are equipped with communication networks for remote control and monitoring purposes. However, the networked systems are susceptible to cyber-attacks, which degrade system operation. This work addresses the cybersecurity problem of cardio-hydro-electromechanical stimulator (C-HEMS) under m...
We propose the Large Organismic Model (LOM), a developmental architecture for artificial intelligence. Rather than reporting the performance of an implemented system, this position paper formulates a testable computational hypothesis that integrates ideas from biology, developmental neuroscience, reinforcement learning...
MCOR-TD3 for MEC-Enabled IIoT — v1.0.1 This release contains Python code associated with the paper "Adaptive Task Caching and Resource Allocation in MEC-Enabled IIoT Using Deep Reinforcement Learning." It supports simulation of cooperative task offloading and computing-resource allocation using MCOR-TD3 to minimize max...
Students in MIT’s Concourse program delve deeply into the human condition, debate challenging questions, and learn to develop judgment about issues that can’t be quantified.
Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them. The post Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses appeared first on Microsoft Research.
The effort aims to help U.S. learners from kindergarten to community college, with an emphasis on math, making, and the constructive use of AI.
Associate Professor Cathy Wu uses reinforcement learning to help map out improvements to transportation and other multifaceted systems.
Mobile Systems
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
