Multi-Agent Hierarchical Reinforcement Learning for Humanoid Navigation

Glen Berseth, Brandon haworth, Seonghyeon Moon, Mubbasir Kapadia, Petros Faloutsos

Keywords: Multi-Agent Reinforcement Learning, Reinforcement Learning, Hierarchical Reinforcement Learning

TL;DR: Improving MARL by sharing task agnostic sub policies.

Abstract:

Multi-agent reinforcement learning is a particularly challenging problem. Current
methods have made progress on cooperative and competitive environments with
particle-based agents. Little progress has been made on solutions that could op-
erate in the real world with interaction, dynamics, and humanoid robots. In this
work, we make a significant step in multi-agent models on simulated humanoid
robot navigation by combining Multi-Agent Reinforcement Learning (MARL)
with Hierarchical Reinforcement Learning (HRL). We build on top of founda-
tional prior work in learning low-level physical controllers for locomotion and
add a layer to learn decentralized policies for multi-agent goal-directed collision
avoidance systems. A video of our results on a multi-agent pursuit environment
can be seen here