Florian Schäfer
  • about
  • people
  • projects
  • publications
  • teaching

Pcgd_arxiv

November 28, 2021

2021

Joint work with Jeffrey, Alistair, Yuanyuan, and Anima now on the arxiv. We extend competitive gradient descent to arbitrary numbers of agents, prove its local convergence, and show that it learns significantly more performant policies when used for multi-agent reinforcement learning.

© Copyright 2023 Florian Schäfer. Powered by Jekyll with al-folio theme. Hosted by GitHub Pages.