Scaling Up Q-Learning via Exploiting State–Action Equivalence
Recent success stories in reinforcement learning have demonstrated that leveraging structural properties of the underlying environment is key in devising viable methods capable of solving complex tasks. We study off-policy learning in discounted reinforcement learning, where some equivalence relatio...
Main Authors: | Yunlian Lyu, Aymeric Côme, Yijie Zhang, Mohammad Sadegh Talebi |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-03-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/25/4/584 |
Similar Items
-
UAV Autonomous Target Search Based on Deep Reinforcement Learning in Complex Disaster Scene
by: Chunxue Wu, et al.
Published: (2019-01-01) -
Making virtual learning environment more intelligent: application of Markov decision process
by: Dalia Baziukaitė
Published: (2004-12-01) -
Multi-Agent Reinforcement Learning with Optimal Equivalent Action of Neighborhood
by: Haixing Wang, et al.
Published: (2022-03-01) -
EFFICIENT SPECTRUM UTILIZATION IN COGNITIVE RADIO THROUGH REINFORCEMENT LEARNING
by: Dhananjay Kumar, et al.
Published: (2013-09-01) -
Double Speedy Q-Learning Based on Successive Over Relaxation
by: ZHOU Qin, LUO Fei, DING Wei-chao, GU Chun-hua, ZHENG Shuai
Published: (2022-03-01)