專題演講 主講人：曾國師教授(中央大學數學系)

  • 事件日期: 2022-04-07
  • 演講者:  /  主持人:
This is an image


題　目：Adaptive Submodular Inverse Reinforcement Learning for Spatial Search and Map Exploration

主講人：曾國師教授(中央大學數學系)

時　間：111年4月7日(星期四)上午11:10-12:00

 
地　點：線上演講－使用Google Meet

使用Google Meet線上直播，
演講開始前20分鐘可進入會議，請點選下列連結後按下「要求加入」即可
摘要
 
Finding optimal paths for spatial search and map exploration problems are NP-hard. Since spatial search and environmental exploration are parts of human central activities, learning human behavior from data is a way to solve these problems. Utilizing the adaptive submodularity of two problems, this research proposes an adaptive submodular inverse reinforcement learning (ASIRL) algorithm to learn human behavior. The ASIRL approach is to learn the reward functions in the Fourier domain and then recover it in the spatial domain. The near-optimal path can be computed through learned reward functions. The experiments demonstrate that the ASIRL outperforms state of the art approaches (e.g., REWARDAGG and QVALAGG).

1/0