Intent-based Deep Reinforcement Learning for Multi-agent Informative Path Planning

TL;DR

This paper introduces a decentralized deep reinforcement learning method with intent sharing and attention mechanisms for multi-agent informative path planning, improving cooperation and performance under communication constraints.

Contribution

It presents a novel intent-based DRL framework with attention mechanisms for multi-agent path planning, addressing prediction noise and communication limitations.

Findings

Outperforms traditional reactive planning methods.

Effective under limited communication ranges.

Enhances cooperation through intent sharing and attention mechanisms.

Abstract

In multi-agent informative path planning (MAIPP), agents must collectively construct a global belief map of an underlying distribution of interest (e.g., gas concentration, light intensity, or pollution levels) over a given domain, based on measurements taken along their trajectory. They must frequently replan their path to balance the exploration of new areas with the exploitation of known high-interest areas, to maximize information gain within a predefined budget. Traditional approaches rely on reactive path planning conditioned on other agents' predicted future actions. However, as the belief is continuously updated, the predicted actions may not match the executed actions, introducing noise and reducing performance. We propose a decentralized, deep reinforcement learning (DRL) approach using an attention-based neural network, where agents optimize long-term individual and cooperative objectives by sharing their intent, represented as a distribution of medium-/long-term future positions obtained from their own policy. Intent sharing enables agents to learn to claim or avoid broader areas, while the use of attention mechanisms allows them to identify useful portions of imperfect predictions, maximizing cooperation even based on imperfect information. Our experiments compare the performance of our approach, its variants, and high-quality baselines across various MAIPP scenarios. We finally demonstrate the effectiveness of our approach under limited communication ranges, towards deployments under realistic communication constraints.