Login / Signup

RL in Markov Games with Independent Function Approximation: Improved Sample Complexity Bound under the Local Access Model.

Junyi FanYuxuan HanJialin ZengJian-Feng CaiYang WangYang XiangJiheng Zhang
Published in: CoRR (2024)
Keyphrases
  • function approximation
  • reinforcement learning
  • upper bound
  • model free
  • sample complexity
  • theoretical analysis
  • learning algorithm
  • lower bound
  • feature vectors
  • learning styles
  • learning tasks