• search
    search
  • reviewers
    reviewers
  • feeds
    feeds
  • assignments
    assignments
  • settings
  • logout

Convergence and Price of Anarchy Guarantees of the Softmax Policy Gradient in Markov Potential Games.

Dingyang ChenQi ZhangThinh T. Doan
Published in: CoRR (2022)
Keyphrases
  • policy gradient
  • markov chain
  • reinforcement learning
  • markov model
  • actor critic
  • game theory
  • convergence rate
  • game playing