4 papers
Training Small LLMs as Spatial Multi-Agent Policies
Yi Mao, Andrew Perrault
Training LLM-based multi-agent systems with multi-agent reinforcement learning is rapidly gaining traction, and a parallel line of work argues that such systems should be judged by…
Learning Provably Correct Distributed Protocols Without Human Knowledge
Yujie Hui, Xiaoyi Lu, Andrew Perrault +1
Provably correct distributed protocols, which are a critical component of modern distributed systems, are highly challenging to design and have often required decades of human effo…
Dreaming Falcon: Physics-Informed Model-Based Reinforcement Learning for Quadcopters
Eashan Vytla, Bhavanishankar Kalavakolanu, Andrew Perrault +1
Current control algorithms for aerial robots struggle with robustness in dynamic environments and adverse conditions. Model-based reinforcement learning (RL) has shown strong poten…
Optimizing Urban Service Allocation with Time-Constrained Restless Bandits
Yi Mao, Andrew Perrault
Municipal inspections are an important part of maintaining the quality of goods and services. In this paper, we approach the problem of intelligently scheduling service inspections…