arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.00882cs.LGcs.AIcs.HC
收藏

人工智能体在人机协作解决问题时是否应该寻求帮助?

Should artificial agents ask for help in human-robot collaborative problem-solving?

ENSTA, Institut Polytechnique Paris(巴黎理工学院ENSTA);Inria(法国国家信息与自动化研究所);Segula Technologies(赛科集团);European Commission, JRC, Centre for Advanced Studies(欧盟委员会联合研究中心高级研究中心)

Adrien Bennetot, Vicky Charisi, Natalia Díaz-Rodríguez

摘要:

尽可能快地将我们大脑的功能转移到人工智能是一个雄心勃勃的目标,这将有助于推进人工智能和机器人技术的发展。正是从这个角度来看,我们建议从来自人类-机器人交互的实证研究的假设开始,并验证它们是否以与基本强化学习算法相同的方式对儿童进行验证。因此,我们检查在解决一个简单的封闭式任务(Hanoi塔)时是否接受专家的帮助可以加速这个任务的学习,这取决于干预是规范的还是玩家要求的。我们的经验使我们得出结论,无论是否被要求,Q-学习算法都能像儿童一样从专家的帮助中受益。

英文摘要:

Transferring as fast as possible the functioning of our brain to artificial intelligence is an ambitious goal that would help advance the state of the art in AI and robotics. It is in this perspective that we propose to start from hypotheses derived from an empirical study in a human-robot interaction and to verify if they are validated in the same way for children as for a basic reinforcement learning algorithm. Thus, we check whether receiving help from an expert when solving a simple close-ended task (the Towers of Hanoï) allows to accelerate or not the learning of this task, depending on whether the intervention is canonical or requested by the player. Our experiences have allowed us to conclude that, whether requested or not, a Q-learning algorithm benefits in the same way from expert help as children do.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑