Learning and exploiting shaped reward models for large scale multiagent RL

• Main Authors: SINGH, Arambam James, KUMAR, Akshat, LAU, Hoong Chuin
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2021
• 主題: Model Representation And Learning Domain Models For Planning; Multi-agent Planning And Learning; Artificial Intelligence and Robotics; Operations Research, Systems Engineering and Industrial Engineering
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/6032; https://ink.library.smu.edu.sg/context/sis_research/article/7035/viewcontent/ICAPS_2021___Learning_Shaped_Reward_Models_for_Large_Scale_Multiagent_RL.pdf

Many real world systems involve interaction among large number of agents to achieve a common goal, for example, air traffic control. Several model-free RL algorithms have been proposed for such settings. A key limitation is that the empirical reward signal in model-free case is not very effective in...