Hierarchical Needs-driven Agent Learning Systems: From Deep Reinforcement Learning To Diverse Strategies

TL;DR

This paper presents a hierarchical needs-driven learning framework for AI agents, integrating deep reinforcement learning with Maslow's needs hierarchy, demonstrated through a novel Bayesian Soft Actor-Critic approach for single and multi-agent systems.

Contribution

It introduces a new hierarchical needs-driven learning system based on deep reinforcement learning and proposes the Bayesian Soft Actor-Critic method for agent evolution.

Findings

Successful implementation in single-robot systems

Extension to multi-agent systems discussed

Potential for diverse strategies development

Abstract

The needs describe the necessities for a system to survive and evolve, which arouses an agent to action toward a goal, giving purpose and direction to behavior. Based on Maslow hierarchy of needs, an agent needs to satisfy a certain amount of needs at the current level as a condition to arise at the next stage -- upgrade and evolution. Especially, Deep Reinforcement Learning (DAL) can help AI agents (like robots) organize and optimize their behaviors and strategies to develop diverse Strategies based on their current state and needs (expected utilities or rewards). This paper introduces the new hierarchical needs-driven Learning systems based on DAL and investigates the implementation in the single-robot with a novel approach termed Bayesian Soft Actor-Critic (BSAC). Then, we extend this topic to the Multi-Agent systems (MAS), discussing the potential research fields and directions.