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...
Váldodahkkit: | , |
---|---|
Eará dahkkit: | |
Materiálatiipa: | Journal Article |
Giella: | English |
Almmustuhtton: |
2022
|
Fáttát: | |
Liŋkkat: | https://hdl.handle.net/10356/162585 |