2 papers
cs.RO2019
Distributed Learning of Decentralized Control Policies for Articulated Mobile Robots
Guillaume Sartoretti, William Paivine, Yunfei Shi +2
State-of-the-art distributed algorithms for reinforcement learning rely on multiple independent agents, which simultaneously learn in parallel environments while asynchronously upd…
cs.RO2018
PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning
Guillaume Sartoretti, Justin Kerr, Yunfei Shi +4
Multi-agent path finding (MAPF) is an essential component of many large-scale, real-world robot deployments, from aerial swarms to warehouse automation. However, despite the commun…