Category
2,236 papers
BRSDK is a deterministic, high-frequency telemetry framework and Python SDK designed to bridge the Simulation-to-Real (Sim2Real) transfer gap in autonomous vehicle engineering, reinforcement learning, and vehicle dynamics within BeamNG.drive and BeamNG.tech.
This repository contains the code, data, and pre-trained models for "MulTADrug-GPT: A sample-efficient generative framework for multi-target drug design via reinforcement and preference learning". For detailed instructions on environment setup and the step-by-step execution of the training and evaluation pipelines, ple...
This study proposes a compact rotary inverted pendulum experimental platform designed for implementing reinforcement learning (RL) based controllers on physical systems. While RL demonstrates superior performance in simulated environments, applying it to real-world systems often leads to performance degradation and ins...
A new framework for flexible, nonlinear, and interpretable off-policy evaluation for infinite-horizon reinforcement learning is developed and a group-sparsity-based feature screening procedure is proposed that identifies, with high probability, a reduced feature set containing all relevant covariates.
Reach audiences
Advertise in front of researchers, engineers, and readers.
The boundaries of how reinforcement learning optimizes the reasoning capabilities of large language models under different resource and scale constraints are reviewed, as well as the adaptability of reinforcement learning's optimization of large language models in different scenarios are analyzed.
Artificial Intelligence and Graph Theory Based Traffic Signal Control Systems for Road Intersections Traffic congestion is a critical and economically damaging problem in dense urban areas, driven by rapid urbanization, rising vehicle density, and — most critically — fixed-time signal strategies that fail to adapt to r...
Artificial Intelligence and Graph Theory Based Traffic Signal Control Systems for Road Intersections Traffic congestion is a critical and economically damaging problem in dense urban areas, driven by rapid urbanization, rising vehicle density, and — most critically — fixed-time signal strategies that fail to adapt to r...
This repository provides the research software, reproducibility materials, benchmark results, and figure-generation resources accompanying the study “Adaptive Anchor-Guided Spherical-Neutrosophic Intelligence for Uncertainty-Aware Engineering Systems.” The package implements and supports the proposed Adaptive Anchor-Gu...
Automated driving system (ADS) deployment requires rigorous validation across safety–critical vehicle–pedestrian interactions, yet real-world datasets rarely capture high-risk scenarios while simulation platforms lack realistic behavior. In response, this study proposes a three-stage framework that combines real-world...
We present a synthesis of the Karimov–Alekberli (KA) Framework into a unified theory ofConstitutional Intelligence: the capacity of an adaptive system to make consequentialdecisions that are simultaneously governed, explainable, accountable, reconstructable,verifiable, and capable of learning without retroactive falsif...
We propose an iterative programmatic planning (IPP) framework that solves grid-based tasks by using large language models (LLMs) to synthesize interpretable, executable programs that act as agent policies mapping environment states to action sequences, rather than relying on traditional search or reinforcement learning...
A new machine-learning approach broke records for weather forecasting for an important time frame in emergency planning.
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics. The post Simulating student learning for better AI tutoring appeared first on Microsoft Research.
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.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
