Scalable Model-based Policy Optimization for Decentralized Networked Systems

Reinforcement learning algorithms require a large amount of samples; this often limits their real-world applications on even simple tasks. Such a challenge is more outstanding in multi-agent tasks, as each step of operation is more costly, requiring communications or shifting or resources. This work aims to improve data efficiency of multi-agent control by model-based learning. We consider networked systems where agents are cooperative and communicate only locally with their neighbors, and propose the decentralized model-based policy optimization framework (DMPO). In our method, each agent learns a dynamic model to predict future states and broadcast their predictions by communication, and then the policies are trained under the model rollouts. To alleviate the bias of model-generated data, we restrain the model usage for generating myopic rollouts, thus reducing the compounding error of model generation. To pertain the independence of policy update, we introduce extended value function and theoretically prove that the resulting policy gradient is a close approximation to true policy gradients. We evaluate our algorithm on several benchmarks for intelligent transportation systems, which are connected autonomous vehicle control tasks (Flow and CACC) and adaptive traffic signal control (ATSC). Empirical results show that our method achieves superior data efficiency and matches the performance of model-free methods using true models. The source code of our algorithm and baselines can be found at https://github.com/PKU-MARL/Model-Based-MARL.

Authors

• Yali Du 0001
• Chengdong Ma
• Yuchen Liu
• Runji Lin
• Hao Dong 0003
• Jun Wang 0012
• Yaodong Yang 0001

Keywords

• Adaptation models
• Source coding
• Reinforcement learning
• Predictive models
• Approximation algorithms
• Data models
• Task analysis
• Network System
• Optimal Policy
• Model-Based Policy Optimization
• Value Function
• Vehicle Control
• Adaptive Control
• Signatures Of Adaptation
• Traffic Control
• Intelligent Transportation
• Operation Steps
• Intelligent Transportation Systems
• Policy Gradient
• Control Of Autonomous Vehicles
• Wireless
• Error Model
• Power Loss
• Local State
• Local Policy
• Unmanned Aerial Vehicles
• Traffic Flow
• Model-based Algorithm
• Multi-agent Reinforcement Learning
• Sampling Efficiency
• Headway
• Communication Cost
• Reward Function
• Policy Learning
• Cooperative Control
• Model-based Methods
• Training Step