Cargando…
End-to-End Autonomous Exploration with Deep Reinforcement Learning and Intrinsic Motivation
Developing artificial intelligence (AI) agents is challenging for efficient exploration in visually rich and complex environments. In this study, we formulate the exploration question as a reinforcement learning problem and rely on intrinsic motivation to guide exploration behavior. Such intrinsic m...
Autores principales: | Ruan, Xiaogang, Li, Peng, Zhu, Xiaoqing, Yu, Hejie, Yu, Naigong |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Hindawi
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8702337/ https://www.ncbi.nlm.nih.gov/pubmed/34956359 http://dx.doi.org/10.1155/2021/9945044 |
Ejemplares similares
-
Editorial: Intrinsically Motivated Open-Ended Learning in Autonomous Robots
por: Santucci, Vieri Giuliano, et al.
Publicado: (2020) -
An End-to-End Deep Reinforcement Learning-Based Intelligent Agent Capable of Autonomous Exploration in Unknown Environments
por: Ramezani Dooraki, Amir, et al.
Publicado: (2018) -
End-to-End Autonomous Navigation Based on Deep Reinforcement Learning with a Survival Penalty Function
por: Jeng, Shyr-Long, et al.
Publicado: (2023) -
A target-driven visual navigation method based on intrinsic motivation exploration and space topological cognition
por: Ruan, Xiaogang, et al.
Publicado: (2022) -
Deep Reinforcement Learning for End-to-End Local Motion Planning of Autonomous Aerial Robots in Unknown Outdoor Environments: Real-Time Flight Experiments
por: Doukhi, Oualid, et al.
Publicado: (2021)