Game-theoretic inverse reinforcement learning: a differential pontryagin's maximum principle approach
This paper proposes a game-theoretic inverse reinforcement learning (GT-IRL) framework, which aims to learn the parameters in both the dynamic system and individual cost function of multistage games from demonstrated trajectories. Different from the probabilistic approaches in computer science commu...
Saved in:
Main Authors: | Cao, Kun, Xie, Lihua |
---|---|
其他作者: | School of Electrical and Electronic Engineering |
格式: | Article |
語言: | English |
出版: |
2022
|
主題: | |
在線閱讀: | https://hdl.handle.net/10356/162585 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
機構: | Nanyang Technological University |
語言: | English |
相似書籍
-
Pontryagin's principle for state-constrained evolutionary differential complementarity system
由: Chen, Q., et al.
出版: (2014) -
Multistage R&D competition and patent policy
由: Lim, W.S.
出版: (2014) -
Game-theoretic multi-agent motion planning in a mixed environment
由: Zhang, Xiaoxue, et al.
出版: (2024) -
Trust-region inverse reinforcement learning
由: Cao, Kun, et al.
出版: (2023) -
A successive convex approximation method for multistage workforce capacity planning problem with turnover
由: Song, H., et al.
出版: (2014)