Login / Signup

SaFormer: A Conditional Sequence Modeling Approach to Offline Safe Reinforcement Learning.

Qin ZhangLinrui ZhangHaoran XuLi ShenBowen WangYongzhe ChangXueqian WangBo YuanDacheng Tao
Published in: CoRR (2023)
Keyphrases
  • reinforcement learning
  • multi agent
  • supervised learning
  • real time
  • real world
  • petri net
  • function approximation
  • modeling method
  • modeling framework
  • hidden state