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

Qin Yang
2/25/2023
cs.AIcs.LGcs.MA

Official code: RickYang2016/Bayesian-Soft-Actor-Critic (13 stars, MIT, last commit 2022-12-28).

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.

View on arXivView PDF

Code Implementations(1)

RickYang2016/Bayesian-Soft-Actor-CriticOfficial67%
MIT

Adopting reasonable strategies is challenging but crucial for an intelligent agent with limited resources working in hazardous, unstructured, and dynamic environments to improve the system utility, decrease the overall cost, and increase mission success probability. Deep Reinforcement Learning (DRL) helps organize agents' behaviors and actions based on their state and represents complex strategies (composition of actions). This research introduces a novel hierarchical strategy decomposition approach based on Bayesian chaining to separate an intricate policy into several simple sub-policies and organize their relationships as Bayesian strategy networks (BSN).

133PythonDec 3, 20213 years agoMIT

Similar Papers

Taxonomy and Trends in Reinforcement Learning for Robotics and Control Systems: A Structured Review

84% match2025

Innate-Values-driven Reinforcement Learning based Cooperative Multi-Agent Cognitive Modeling

83% match2024

Proposing Hierarchical Goal-Conditioned Policy Planning in Multi-Goal Reinforcement Learning

82% match2025

Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics

82% match1 repo252026

Combining Bayesian Inference and Reinforcement Learning for Agent Decision Making: A Review

82% match2025

Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments

82% match1 repo2.8k2017

Cite this paper

@article{yang2023hierarchical,
  title  = {Hierarchical Needs-driven Agent Learning Systems: From Deep Reinforcement Learning To Diverse Strategies},
  author = {Qin Yang},
  year   = {2023},
  eprint = {2302.13132},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2302.13132v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2302.13132.svg)](https://codeofpaper.com/paper/2302.13132)

Discussion