mlsanityData to 7 Oct 2026

Optimize Neural Fictitious Self-Play in Regret Minimization Thinking

arXiv 2104.10845 ↗First posted 22 Apr 2021cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Optimization of deep learning algorithms to approach Nash Equilibrium remains a significant problem in imperfect information games, e.g. StarCraft and poker. Neural Fictitious Self-Play (NFSP) has provided an effective way to learn approximate Nash Equilibrium without prior domain knowledge in imperfect information games. However, optimality gap was left as an optimization problem of NFSP and by solving the problem, the performance of NFSP could be improved. In this study, focusing on the optimality gap of NFSP, we have proposed a new method replacing NFSP's best response computation with regret matching method. The new algorithm can make the optimality gap converge to zero as it iterates, thus converge faster than original NFSP. We have conduct experiments on three typical environments of perfect-information games and imperfect information games in OpenSpiel and all showed that our new algorithm performances better than original NFSP.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 11 of its 31 references that are in the map. First posted on arXiv 22 Apr 2021.

Builds on

11 of 31 references.

References · 11

  1. 2015Trust Region Policy Optimizationcited by 2,503
  2. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,084
  3. 2015End-to-End Training of Deep Visuomotor Policiescited by 847
  4. 2019OpenSpiel: A Framework for Reinforcement Learning in Gamescited by 180
  5. 2016Deep Reinforcement Learning from Self-Play in Imperfect-Information Gamescited by 153
  6. 2016Control of Memory, Active Perception, and Action in Minecraftcited by 61
  7. 2019AlphaStar: An Evolutionary Computation Perspectivecited by 50
  8. 2017ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Gamescited by 16
  9. 2017Regret Minimization for Partially Observable Deep Reinforcement Learningcited by 12
  10. 2018Qualitative Measurements of Policy Discrepancy for Return-Based Deep Q-Networkcited by 4
  11. 2019Neural Fictitious Self-Play on ELF Mini-RTScited by 1

Built on by

Not cited yet.