Litcius/Paper detail

Deep Multitask Multiagent Reinforcement Learning With Knowledge Transfer

Yuxiang Mai, Yifan Zang, Qiyue Yin, Wancheng Ni, Kaiqi Huang

2023IEEE Transactions on Games13 citationsDOI

Abstract

Despite the potential of Multi-Agent Reinforcement Learning (MARL) in addressing numerous complex tasks, training a single team of MARL agents to handle multiple diverse team tasks remains a challenge. In this paper, we introduce a novel Multi-task method based on Knowledge Transfer in cooperative MARL (MKT-MARL). By learning from task-specific teachers, our approach empowers a single team of agents to attain expert-level performance in multiple tasks. MKT-MARL utilizes a knowledge distillation algorithm specifically designed for the multi-agent architecture, which rapidly learns a team control policy incorporating common coordinated knowledge from the experience of task-specific teachers. Additionally, we enhance this training with teacher annealing, gradually shifting the model's learning from distillation towards environmental rewards. This enhancement helps the multi-task model surpass its single-task teachers. We extensively evaluate our algorithm using two commonly-used benchmarks: StarCraft II micro-management and multi-agent particle environment. The experimental results demonstrate that our algorithm outperforms both the single-task teachers and a jointly-trained team of agents. Extensive ablation experiments illustrate the effectiveness of the supervised knowledge transfer and the teacher annealing strategy.

Topics & Concepts

Computer scienceReinforcement learningTransfer of learningTask (project management)Artificial intelligenceKnowledge transferMachine learningHuman–computer interactionKnowledge managementEngineeringSystems engineeringReinforcement Learning in RoboticsMobile Crowdsensing and Crowdsourcing
Deep Multitask Multiagent Reinforcement Learning With Knowledge Transfer | Litcius