Login / Signup

Modeling Socially Normative Navigation Behaviors from Demonstrations with Inverse Reinforcement Learning.

Xingyuan GaoXiaoguang ZhaoMin Tan
Published in: CASE (2019)
Keyphrases
  • inverse reinforcement learning
  • preference elicitation
  • multi agent systems
  • partially observable environments
  • learning algorithm
  • sufficient conditions
  • monte carlo
  • reward function