Corpus ID: 211069002

Provable Self-Play Algorithms for Competitive Reinforcement Learning

@inproceedings{Bai2020ProvableSA,
  title={Provable Self-Play Algorithms for Competitive Reinforcement Learning},
  author={Yu Bai and C. Jin},
  booktitle={ICML},
  year={2020}
}

Yu Bai, C. Jin

Published in ICML 2020

Computer Science, Mathematics

Self-play, where the algorithm learns by playing against itself without requiring any direct supervision, has become the new weapon in modern Reinforcement Learning (RL) for achieving superhuman performance in practice. However, the majority of exisiting theory in reinforcement learning only applies to the setting where the agent plays against a fixed environment; it remains largely open whether self-play algorithms can be provably effective, especially when it is necessary to manage the… CONTINUE READING

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed