Intelligent Robot Learning Laboratory (IRL Lab) Zhaodong Wang

photo

CONTACT INFORMATION:

Zhaodong Wang
PhD Student, Computer Science
Email: zhaodong.wang@wsu.edu
Office: Dana Hall 3


My Story

My name is Zhaodong Wang. I am a Ph.D. student currently working with Dr. Matthew E. Taylor since 2014. I obtained my bachelor degree of Electrical Engineering from University of Science and Technology of China in 2014.

My Research

My interested researches include Reinforcement Learning, Transfer Learning and Real Robotics. I am mostly motivated by AI and Robotics related techniques changing human’s life.

Current Projects

By: Zhaodong Wang and Matthew E. Taylor

The purpose of this project is to build an intelligent multi-robot system to manage the usage of bins for harvest work in orchard. It is involved with the auto navigation of robots in orchard environment and the cooperation with human pickers. The value of this multi-robot bin managing system is in realizing the autonomous work of robots in tough outdoor environment and improving the harvest efficiency for the agriculture work. [1]

[1] [pdf] Yawei Zhang, Yunxiang Ye, Zhaodong Wang, Matthew E. Taylor, Geoffrey A. Hollinger, and Qin Zhang. Intelligent In-Orchard Bin-Managing System for Tree Fruit Production. In Proceedings of the Robotics in Agriculture workshop (at ICRA), May 2015.
[Bibtex]
@inproceedings{2015ICRA-Zhang,
author={Yawei Zhang and Yunxiang Ye and Zhaodong Wang and Matthew E. Taylor and Geoffrey A. Hollinger and Qin Zhang},
title={{Intelligent In-Orchard Bin-Managing System for Tree Fruit Production}},
booktitle={{Proceedings of the Robotics in Agriculture workshop (at {ICRA})}},
month={May},
year={2015},
bib2html_pubtype={Refereed Workshop or Symposium},
abstract={The labor-intensive nature of harvest in the tree fruit industry makes it particularly sensitive to labor shortages. Technological innovation is thus critical in order to meet current demands without significantly increasing prices. This paper introduces a robotic system to help human workers during fruit harvest. A second-generation prototype is currently being built and simulation results demonstrate potential improvement in productivity.}
}

By: Zhaodong Wang and Matthew E. Taylor

Many learning methods such as reinforcement learning suffers from a slow beginning especially in complicated domains. The motivation of transfer learning is to use limited prior knowledge to help learning agents bootstrap at the start and thus achieve overall improvements on learning performance. Due to limited quantity or quality of prior knowledge, how to make the transfer more efficient and effective remains an interesting point. [1]

[1] [pdf] Zhaodong Wang and Matthew E. Taylor. Effective Transfer via Demonstrations in Reinforcement Learning: A Preliminary Study. In AAAI 2016 Spring Symposium, March 2016.
[Bibtex]
@inproceedings{2016AAAI-SSS-Wang,
author={Zhaodong Wang and Matthew E. Taylor},
title={{Effective Transfer via Demonstrations in Reinforcement Learning: A Preliminary Study}},
booktitle={{{AAAI} 2016 Spring Symposium}},
month={March},
year={2016},
bib2html_pubtype={Refereed Workshop or Symposium},
abstract={There are many successful methods for transferring information from one agent to another. One approach, taken in this work, is to have one (source) agent demonstrate a policy to a second (target) agent, and then have that second agent improve upon the policy. By allowing the target agent to observe the source agent's demonstrations, rather than relying on other types of direct knowledge transfer like Q-values, rules, or shared representations, we remove the need for the agents to know anything about each other's internal representation or have a shared language. In this work, we introduce a refinement to HAT, an existing transfer learning method, by integrating the target agent's confidence in its representation of the source agent's policy. Results show that a target agent can effectively 1) improve its initial performance relative to learning without transfer (jumpstart) and 2) improve its performance relative to the source agent (total reward). Furthermore, both the jumpstart and total reward are improved with this new refinement, relative to learning without transfer and relative to learning with HAT.}
}

Videos & Other Media:

News

Publications

2016

  • Zhaodong Wang and Matthew E. Taylor. Effective Transfer via Demonstrations in Reinforcement Learning: A Preliminary Study. In AAAI 2016 Spring Symposium, March 2016.
    [BibTeX] [Abstract] [Download PDF]

    There are many successful methods for transferring information from one agent to another. One approach, taken in this work, is to have one (source) agent demonstrate a policy to a second (target) agent, and then have that second agent improve upon the policy. By allowing the target agent to observe the source agent’s demonstrations, rather than relying on other types of direct knowledge transfer like Q-values, rules, or shared representations, we remove the need for the agents to know anything about each other’s internal representation or have a shared language. In this work, we introduce a refinement to HAT, an existing transfer learning method, by integrating the target agent’s confidence in its representation of the source agent’s policy. Results show that a target agent can effectively 1) improve its initial performance relative to learning without transfer (jumpstart) and 2) improve its performance relative to the source agent (total reward). Furthermore, both the jumpstart and total reward are improved with this new refinement, relative to learning without transfer and relative to learning with HAT.

    @inproceedings{2016AAAI-SSS-Wang,
    author={Zhaodong Wang and Matthew E. Taylor},
    title={{Effective Transfer via Demonstrations in Reinforcement Learning: A Preliminary Study}},
    booktitle={{{AAAI} 2016 Spring Symposium}},
    month={March},
    year={2016},
    bib2html_pubtype={Refereed Workshop or Symposium},
    abstract={There are many successful methods for transferring information from one agent to another. One approach, taken in this work, is to have one (source) agent demonstrate a policy to a second (target) agent, and then have that second agent improve upon the policy. By allowing the target agent to observe the source agent's demonstrations, rather than relying on other types of direct knowledge transfer like Q-values, rules, or shared representations, we remove the need for the agents to know anything about each other's internal representation or have a shared language. In this work, we introduce a refinement to HAT, an existing transfer learning method, by integrating the target agent's confidence in its representation of the source agent's policy. Results show that a target agent can effectively 1) improve its initial performance relative to learning without transfer (jumpstart) and 2) improve its performance relative to the source agent (total reward). Furthermore, both the jumpstart and total reward are improved with this new refinement, relative to learning without transfer and relative to learning with HAT.}
    }

2015

  • Yawei Zhang, Yunxiang Ye, Zhaodong Wang, Matthew E. Taylor, Geoffrey A. Hollinger, and Qin Zhang. Intelligent In-Orchard Bin-Managing System for Tree Fruit Production. In Proceedings of the Robotics in Agriculture workshop (ICRA), May 2015.
    [BibTeX] [Abstract] [Download PDF]

    The labor-intensive nature of harvest in the tree fruit industry makes it particularly sensitive to labor shortages. Technological innovation is thus critical in order to meet current demands without significantly increasing prices. This paper introduces a robotic system to help human workers during fruit harvest. A second-generation prototype is currently being built and simulation results demonstrate potential improvement in productivity.

    @inproceedings{2015ICRA-Zhang,
    author={Yawei Zhang and Yunxiang Ye and Zhaodong Wang and Matthew E. Taylor and Geoffrey A. Hollinger and Qin Zhang},
    title={{Intelligent In-Orchard Bin-Managing System for Tree Fruit Production}},
    booktitle={{Proceedings of the Robotics in Agriculture workshop ({ICRA})}},
    month={May},
    year={2015},
    bib2html_pubtype={Refereed Workshop or Symposium},
    abstract={The labor-intensive nature of harvest in the tree fruit industry makes it particularly sensitive to labor shortages. Technological innovation is thus critical in order to meet current demands without significantly increasing prices. This paper introduces a robotic system to help human workers during fruit harvest. A second-generation prototype is currently being built and simulation results demonstrate potential improvement in productivity.}
    }