Timezone: »
Fairness is essential for human society, contributing to stability and productivity. Similarly, fairness is also the key for many multi-agent systems. Taking fairness into multi-agent learning could help multi-agent systems become both efficient and stable. However, learning efficiency and fairness simultaneously is a complex, multi-objective, joint-policy optimization. To tackle these difficulties, we propose FEN, a novel hierarchical reinforcement learning model. We first decompose fairness for each agent and propose fair-efficient reward that each agent learns its own policy to optimize. To avoid multi-objective conflict, we design a hierarchy consisting of a controller and several sub-policies, where the controller maximizes the fair-efficient reward by switching among the sub-policies that provides diverse behaviors to interact with the environment. FEN can be trained in a fully decentralized way, making it easy to be deployed in real-world applications. Empirically, we show that FEN easily learns both fairness and efficiency and significantly outperforms baselines in a variety of multi-agent scenarios.
Author Information
Jiechuan Jiang (Peking University)
Zongqing Lu (Peking University)
More from the Same Authors
-
2022 Poster: Model-Based Opponent Modeling »
XiaoPeng Yu · Jiechuan Jiang · Wanpeng Zhang · Haobin Jiang · Zongqing Lu -
2022 Poster: Learning to Share in Networked Multi-Agent Reinforcement Learning »
Yuxuan Yi · Ge Li · Yaowei Wang · Zongqing Lu -
2022 Poster: Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination »
Jiafei Lyu · Xiu Li · Zongqing Lu -
2022 Poster: I2Q: A Fully Decentralized Q-Learning Algorithm »
Jiechuan Jiang · Zongqing Lu -
2022 Poster: Mildly Conservative Q-Learning for Offline Reinforcement Learning »
Jiafei Lyu · Xiaoteng Ma · Xiu Li · Zongqing Lu -
2022 Poster: Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning »
Yuanpei Chen · Tianhao Wu · Shengjie Wang · Xidong Feng · Jiechuan Jiang · Zongqing Lu · Stephen McAleer · Hao Dong · Song-Chun Zhu · Yaodong Yang -
2022 : State Advantage Weighting for Offline RL »
Jiafei Lyu · aicheng Gong · Le Wan · Zongqing Lu · Xiu Li -
2023 Poster: Learning to Ignore: Mutual-Information Regularized Multi-Agent Policy Iteration »
Jiangxing Wang · Deheng Ye · Zongqing Lu -
2023 Poster: Learning from Visual Observation via Offline Pretrained State-to-Go Transformer »
Bohan Zhou · Ke Li · Jiechuan Jiang · Zongqing Lu -
2022 Spotlight: Mildly Conservative Q-Learning for Offline Reinforcement Learning »
Jiafei Lyu · Xiaoteng Ma · Xiu Li · Zongqing Lu -
2022 Spotlight: Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination »
Jiafei Lyu · Xiu Li · Zongqing Lu -
2022 Spotlight: Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning »
Yuanpei Chen · Tianhao Wu · Shengjie Wang · Xidong Feng · Jiechuan Jiang · Zongqing Lu · Stephen McAleer · Hao Dong · Song-Chun Zhu · Yaodong Yang -
2020 Poster: Learning Individually Inferred Communication for Multi-Agent Cooperation »
gang Ding · Tiejun Huang · Zongqing Lu -
2020 Oral: Learning Individually Inferred Communication for Multi-Agent Cooperation »
gang Ding · Tiejun Huang · Zongqing Lu -
2018 Poster: Learning Attentional Communication for Multi-Agent Cooperation »
Jiechuan Jiang · Zongqing Lu