Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces

Author:

Warnell Garrett,Waytowich Nicholas,Lawhern Vernon,Stone Peter

Abstract

While recent advances in deep reinforcement learning have allowed autonomous learning agents to succeed at a variety of complex tasks, existing algorithms generally require a lot oftraining data. One way to increase the speed at which agent sare able to learn to perform tasks is by leveraging the input of human trainers. Although such input can take many forms, real-time, scalar-valued feedback is especially useful in situations where it proves difficult or impossible for humans to provide expert demonstrations. Previous approaches have shown the usefulness of human input provided in this fashion (e.g., the TAMER framework), but they have thus far not considered high-dimensional state spaces or employed the use of deep learning. In this paper, we do both: we propose DeepTAMER, an extension of the TAMER framework that leverages the representational power of deep neural networks inorder to learn complex tasks in just a short amount of time with a human trainer. We demonstrate Deep TAMER’s success by using it and just 15 minutes of human-provided feedback to train an agent that performs better than humans on the Atari game of Bowling - a task that has proven difficult for even state-of-the-art reinforcement learning methods.

Publisher

Association for the Advancement of Artificial Intelligence (AAAI)

Subject

General Medicine

Cited by 25 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. SafeDRL: Dynamic Microservice Provisioning With Reliability and Latency Guarantees in Edge Environments;IEEE Transactions on Computers;2024-01

2. Ask-AC: An Initiative Advisor-in-the-Loop Actor–Critic Framework;IEEE Transactions on Systems, Man, and Cybernetics: Systems;2023-12

3. Primitive Skill-Based Robot Learning from Human Evaluative Feedback;2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS);2023-10-01

4. Bootstrapping Adaptive Human-Machine Interfaces with Offline Reinforcement Learning;2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS);2023-10-01

5. Model-based Adversarial Imitation Learning from Demonstrations and Human Reward;2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS);2023-10-01

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3