Microsoft

Agent Lightning

We present Agent Lightning (opens in new tab), a flexible and extensible framework that enables seamless agent optimization for any existing agent framework. Here agent optimization includes various ...
Microsoft

Microsoft at NeurIPS 2024: Advancing AI research across domains

The event gathers researchers, industry leaders, and practitioners to exchange ideas, address challenges, and advance innovations to shape the future of AI. Lidong Zhou, managing director of Microsoft ...
IEEE

Single-Agent Attention Actor–Critic: A Deep Reinforcement Learning-Based Solution for Low-Thrust Spacecraft Trajectory Optimization

Abstract: This article introduces a deep reinforcement learning (DRL)-based approach for autonomous planning of low-thrust spacecraft trajectories, while addressing the intricate challenges of orbital ...
IEEE

Lyapunov-Informed Multi-Agent Reinforcement Learning for Multi-Robot Cooperation Tasks

Abstract: Multi-Agent Reinforcement Learning (MARL) has shown great potential in solving complex tasks. Despite great success, low training efficiency remains a pervasive and long-standing challenge ...
GitHub

R3DM: Enabling Role Discovery and Diversity Through Dynamics Models in Multi-agent Reinforcement Learning

This repository contains the official implementation for R3DM accepted at the International Conference on Machine Learning (ICML) 2025. It includes the source code for the ACORM and R3DM algorithms, ...