Self-Adaptive Priority Correction for Prioritized Experience Replay

Self-Adaptive Priority Correction for Prioritized Experience Replay

Deep Reinforcement Learning (DRL) is a promising approach for general artificial intelligence. However, most DRL methods suffer from the problem of data inefficiency. To alleviate this problem, DeepMind proposed Prioritized Experience Replay (PER). Though PER improves data utilization, the prioritie...

Full description

Bibliographic Details
Main Authors: Hongjie Zhang, Cheng Qu, Jindou Zhang, Jing Li
Format: Article
Language:English
Published: MDPI AG 2020-10-01
Series:Applied Sciences
Subjects:
deep reinforcement learning
experience replay
importance sampling
DDQN
DDPG
Online Access:https://www.mdpi.com/2076-3417/10/19/6925

Internet

https://www.mdpi.com/2076-3417/10/19/6925

Similar Items