跳到正文
arXiv cs.MA· Ayman bin Kamruddin, Christopher Lam, Gaurav Patil, Mirco Musolesi, Mario di Bernardo, Michael J. Richardson·· 23 小时前AI 评分18

启发式、人类敏感与自博弈 DRL 策略在人机协作中的对比研究

A Comparison of Heuristic, Human-Sensitive, and Self-Play DRL Policies in Human-Agent Teaming

AI 导读

一项 arXiv 论文比较了三种目标选择策略驱动的 DPMP 智能体在第一人称放牧任务中的表现:人类启发式策略、自博弈 DRL(SP-DRL)与和启发式智能体共同训练的人类敏感 DRL(HS-DRL)。结果显示启发式智能体最贴近典型人类-人类协作模式,HS-DRL 次之,SP-DRL 偏离最大。研究认为 DRL 队友训练需引入人类信息,简单启发式策略仍是设计人类对齐 AI 智能体的有效途径。

正文 · 原文

View PDF HTML (experimental)

Abstract:Dynamical Perceptual-Motor Primitives (DPMPs) offer a tractable framework for generating human-like movement dynamics in artificial agents (AAs) and have been used to support coordination in human-AI teaming tasks. Traditionally, DPMP controllers rely on heuristic (rule-based) decision policies derived from human behavior to guide goal selection and action sequencing. Although effective in structured tasks, such heuristics can be difficult to generalize to more complex settings, motivating interest in deep reinforcement learning (DRL) approaches for learning decision policies for human-AI interaction. A key challenge, however, is ensuring that DRL policies remain aligned with human strategies, particularly when agents are trained through self-play. To examine this issue, we compared three target-selection policies governing DPMP-based AAs in a first-person herding task: (1) a human-derived heuristic policy, (2) a self-play DRL policy (SP-DRL), and (3) a human-sensitive DRL policy (HS-DRL) trained alongside a heuristic agent. Results showed that heuristic agents most closely matched typical human-human coordination patterns, followed by HS-DRL agents, whereas SP-DRL agents deviated most. These findings highlight the importance of human-informed training when developing DRL-based teammates and suggest that simple heuristic policies may remain an effective approach for designing human-aligned AAs capable of human-AI collaboration.
Comments: 9 pages, 5 figures. Includes Supplementary Material A (1 page, 0 figures), B (1 page, 0 figures), and C (54 pages, 216 figures). Submitted to IEEE HMS for possible publication
Subjects: Multiagent Systems (cs.MA); Human-Computer Interaction (cs.HC)
Cite as: arXiv:2611.23747 [cs.MA]
  (or arXiv:2611.23747v1 [cs.MA] for this version)
  https://doi.org/10.48550/arXiv.2611.23747

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Christopher Lam [view email]
[v1] Wed, 18 Nov 2026 02:59:54 UTC (12,560 KB)

来源:arXiv cs.MA · arxiv.org