Concepedia

Distributed Policy Optimization

Distributed Policy Optimization is a distributed reinforcement learning framework that coordinates policy updates across multiple agent-specific learners through decentralized optimization, distinguishing itself from centralized approaches by enabling scalable, asynchronous, and communication-efficient training in multi-robot systems.

14

Publications

619

Citations

53

Authors

24

Institutions

Publications per year

2017–2026

14

Parents

Publications

14

DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion\n Frames

Erik Wijmans, Abhishek Kadian, Ari S. Morcos et al. · arXiv (Cornell University) · 2019 · 171 citations · Full text

, , +16

UAV-Enabled Covert Federated Learning

Xiangwang Hou, Jingjing Wang, Chunxiao Jiang et al. · IEEE Transactions on Wireless Communications · 2023 · 121 citations

, , +14

Communication-Efficient Policy Gradient Methods for Distributed Reinforcement Learning

Tianyi Chen, Kaiqing Zhang, Georgios B. Giannakis et al. · IEEE Transactions on Control of Network Systems · 2021 · 58 citations

, , +16

Efficient and scalable reinforcement learning for large-scale network control

Chengdong Ma, Aming Li, Yali Du et al. · Nature Machine Intelligence · 2024 · 56 citations · Full text

, , +16

Distributed Reinforcement Learning for Decentralized Linear Quadratic Control: A Derivative-Free Policy Optimization Approach

Yingying Li, Yujie Tang, Runyu Zhang et al. · IEEE Transactions on Automatic Control · 2021 · 37 citations · Full text

, , +16

1–5 of 14

Authors

53

  1. AK
    Abhishek Kadian

    Georgia Institute of Technology, United States

    3 publications · 222 citations

    3

    h-index

  2. DP
    Devi Parikh

    Georgia Institute of Technology, United States

    3 publications · 222 citations

    3

    h-index

  3. DB
    Dhruv Batra

    Georgia Institute of Technology, United States

    3 publications · 222 citations

    3

    h-index

  4. AS
    Ari S. Morcos

    Meta (Israel), Israel

    3 publications · 222 citations

    3

    h-index

  5. MS
    Manolis Savva

    Stanford University, United States

    3 publications · 222 citations

    3

    h-index

1–5 of 53

Institutions

24

  1. Harvard University Press

    Cambridge, United States

    2 h-index

    5 publications

    184 citations

  2. Tianjin University

    Tianjin, China

    2 h-index

    5 publications

    81 citations

  3. University of Minnesota

    Minneapolis, United States

    2 h-index

    3 publications

    82 citations

  4. Simon Fraser University

    Burnaby, Canada

    1 h-index

    1 publications

    36 citations

  5. Duke University

    Durham, United States

    1 h-index

    2 publications

    46 citations

  6. Oregon State University

    Corvallis, United States

    1 h-index

    1 publications

    36 citations

  7. Beihang University

    Beijing, China

    1 h-index

    1 publications

    121 citations

  8. Florida International University

    Miami, United States

    1 h-index

    3 publications

    48 citations

1–8 of 24

Venues

  1. arXiv (Cornell University)

    Repository · 5 publications · 254 citations

    5

    h-index

  2. IEEE Transactions on Automatic Control

    2 publications · 60 citations

    2

    h-index

  3. 1

    h-index

  4. Computer-Aided Civil and Infrastructure Engineering

    CACAIE · 1 publications · 29 citations

    1

    h-index

  5. Journal of Computer Science and Technology

    1 publications · 13 citations

    1

    h-index

1–5