Cargando…
Real-Time Online Goal Recognition in Continuous Domains via Deep Reinforcement Learning
The problem of goal recognition involves inferring the high-level task goals of an agent based on observations of its behavior in an environment. Current methods for achieving this task rely on offline comparison inference of observed behavior in discrete environments, which presents several challen...
Autores principales: | Fang, Zihao, Chen, Dejun, Zeng, Yunxiu, Wang, Tao, Xu, Kai |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10606411/ https://www.ncbi.nlm.nih.gov/pubmed/37895536 http://dx.doi.org/10.3390/e25101415 |
Ejemplares similares
-
Single Real Goal, Magnitude-Based Deceptive Path-Planning
por: Xu, Kai, et al.
Publicado: (2020) -
Adaptive Discount Factor for Deep Reinforcement Learning in Continuing Tasks with Uncertainty
por: Kim, MyeongSeop, et al.
Publicado: (2022) -
Pattern recognition of topologically associating domains using deep learning
por: Yang, Jhen Yuan, et al.
Publicado: (2022) -
Humans perseverate on punishment avoidance goals in multigoal reinforcement learning
por: Sharp, Paul B, et al.
Publicado: (2022) -
Deep Learning-Based Real-Time Multiple-Person Action Recognition System
por: Tsai, Jen-Kai, et al.
Publicado: (2020)