Thayne T. Walker, Jaime S. Ide, Minkyu Choi, Michael John Guarino, and Kevin Alcedo.
International Conference on Control, Decision and Information Technologies (CoDit), 2023

The coordination of multiple autonomous agents is essential for achieving collaborative goals efficiently, especially in environments with limited communication and sensing capabilities. Our recent study, presented at CoDIT 2023, explores a novel method to tackle this challenge. We introduce Multi-Agent Reinforcement Learning with Epistemic Priors (MARL-EP), a technique that leverages shared mental models to enable high-level coordination among agents, even with severely impaired sensing and zero communication.

Distilling Reinforcement Learning

The paper introduces a hierarchical reinforcement learning framework called Feudal Networks (FuN) that enables agents to learn a hierarchy of temporal abstractions. The proposed model consists of a Manager and a Worker, with the Manager learning high-level policies and the Worker learning low-level policies. The approach is demonstrated to achieve state-of-the-art performance on a range of challenging tasks in the Atari domain.

Minkyu Choi, Max Filter, Kevin, Alcedo, Thayne T. Walker, David Rosenbluth, and Jaime S. Ide.
International Conference on Unmanned Aircraft Systems (ICUAS), 2022

The rapid evolution in autonomous unmanned aerial vehicles (UAVs) technology has spurred significant advancements in their control systems. A prominent challenge in this domain is balancing the agility of Proportional-Integral-Derivative (PID) systems for low-level control with the adaptability of Deep Reinforcement Learning (DRL) for navigation through complex environments. This post delves into a novel approach that combines these technologies to improve the retraining efficiency of UAV controllers using Soft Actor-Critic (SAC) with inhibitory networks.