mlsanityData to 7 Oct 2026

Improving Model and Search for Computer Go

arXiv 2102.03467 ↗First posted 6 Feb 2021cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

The standard for Deep Reinforcement Learning in games, following Alpha Zero, is to use residual networks and to increase the depth of the network to get better results. We propose to improve mobile networks as an alternative to residual networks and experimentally show the playing strength of the networks according to both their width and their depth. We also propose a generalization of the PUCT search algorithm that improves on PUCT.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 8 of its 16 references that are in the map. First posted on arXiv 6 Feb 2021.

Builds on

8 of 16 references.

References · 8

  1. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  2. 2017Squeeze-and-Excitation Networkscited by 4,763
  3. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  4. 2017Thinking Fast and Slow with Deep Learning and Tree Searchcited by 245
  5. 2019Accelerating Self-Play Learning in Gocited by 60
  6. 2019ELF OpenGo: An Analysis and Open Reimplementation of AlphaZerocited by 37
  7. 2020Polygames: Improved Zero Learningcited by 11
  8. 2020Mobile Networks for Computer Gocited by 5

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1; 2023: 1.

3 papers.

  1. 2022DouZero+: Improving DouDizhu AI by Opponent Modeling and Coach-guided Learningcited by 7
  2. 2021Batch Monte Carlo Tree Searchcited by 5
  3. 2023Vision Transformers for Computer Gocited by 2