Work

Multi-Agent/Robot Deep Reinforcement Learning with Macro-Actions (Student Abstract)

Year: 2020

Type: conference-paper

Abstract: We consider the challenges of learning multi-agent/robot macro-action-based deep Q-nets including how to properly update each macro-action value and accurately maintain macro-action-observation trajectories. We address these challenges by first proposing two fundamental frameworks for learning macro-action-value function and joint macro-action-value function. Furthermore, we present two new approaches of learning decentralized macro-action-based policies, which involve a new double Q-update rule that facilitates the learning of decentralized Q-nets by using a centralized Q-net for action selection. Our approaches are evaluated both in simulation and on real robots.

Source: Proceedings of the AAAI Conference on Artificial Intelligence

DOI: 10.1609/aaai.v34i10.7255

Authors: Yuchen Xiao, Joshua Hoffman, Tian Xia, Christopher Amato

Institution: Northeastern University

Language: English

Topic: Reinforcement Learning in Robotics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: diamond

OpenAlex ID: W3037510552

FWCI: 0.191

Cites: 7

Cited by: 2

Related to: 10