Noisy sensing, imperfect control, and environment changes are defining characteristics of
many real-world robot tasks. The partially observable Markov decision process (POMDP) …

Significant advances have recently been achieved in Multi-Agent Reinforcement Learning
(MARL) which tackles sequential decision-making problems involving multiple participants …

Multi-agent Reinforcement Learning (MARL) has gained wide attention in recent years and
has made progress in various fields. Specifically, cooperative MARL focuses on training a …

Synchronizing decisions across multiple agents in realistic settings is problematic since it
requires agents to wait for other agents to terminate and communicate about termination …

Given the popular presupposition of human reasoning as the standard for learning and
decision making, there have been significant efforts and a growing trend in research to …

Decentralized multi-robot systems typically perform coordinated motion planning by
constantly broadcasting their intentions to avoid collisions. However, the risk of collision …

The primary challenge in the development of large-scale artificial intelligence (AI) systems
lies in achieving scalable decision-making—extending the AI models while maintaining …

Reinforcement learning (RL) in partially observable, fully cooperative multi-agent settings
(Dec-POMDPs) can in principle be used to address many real-world challenges such as …

We propose a decentralized, learning-based solution to the challenging problem of
unlabeled multi-agent navigation among obstacles, where robots need to simultaneously …

We investigate pneumatic non-prehensile manipulation (ie, blowing) as a means of
efficiently moving scattered objects into a target receptacle. Due to the chaotic nature of …