CuMARL: Curiosity-Based Learning in Multiagent Reinforcement Learning

CuMARL: Curiosity-Based Learning in Multiagent Reinforcement Learning

In this paper, we propose a novel curiosity-based learning algorithm for Multi-agent Reinforcement Learning (MARL) to attain efficient and effective decision-making. We employ the centralized training with decentralized execution framework (CTDE) and consider that each agent has knowledge of the pri...

Celý popis

Podrobná bibliografie
Hlavní autoři: Devarani Devi Ningombam, Byunghyun Yoo, Hyun Woo Kim, Hwa Jeon Song, Sungwon Yi
Médium: Článek
Jazyk:English
Vydáno: IEEE 2022-01-01
Edice:IEEE Access
Témata:
Multi-agent reinforcement learning
curiosity
conditional mutual information
prioritized experience replay
On-line přístup:https://ieeexplore.ieee.org/document/9857920/

Internet

https://ieeexplore.ieee.org/document/9857920/

Podobné jednotky