Data-efficient model-based reinforcement learning with trajectory discrimination
Abstract Deep reinforcement learning has always been used to solve high-dimensional complex sequential decision problems. However, one of the biggest challenges for reinforcement learning is sample efficiency, especially for high-dimensional complex problems. Model-based reinforcement learning can s...
Main Authors: | Tuo Qu, Fuqing Duan, Junge Zhang, Bo Zhao, Wenzhen Huang |
---|---|
Format: | Article |
Language: | English |
Published: |
Springer
2023-10-01
|
Series: | Complex & Intelligent Systems |
Subjects: | |
Online Access: | https://doi.org/10.1007/s40747-023-01247-5 |
Similar Items
-
A Survey of Multi-Task Deep Reinforcement Learning
by: Nelson Vithayathil Varghese, et al.
Published: (2020-08-01) -
Computation Offloading and Trajectory Control for UAV-Assisted Edge Computing Using Deep Reinforcement Learning
by: Huamei Qi, et al.
Published: (2022-12-01) -
Optimizing trajectories for highway driving with offline reinforcement learning
by: Branka Mirchevska, et al.
Published: (2023-05-01) -
MRLCC: an adaptive cloud task scheduling method based on meta reinforcement learning
by: Xi Xiu, et al.
Published: (2023-05-01) -
Corrigendum: Optimizing trajectories for highway driving with offline reinforcement learning
by: Branka Mirchevska, et al.
Published: (2023-12-01)