Multi-agent Reinforcement Learning for Networked System Control

2020-04-03 · ICLR 2020 1 · Tianshu Chu, Sandeep Chinchali, Sachin Katti

This paper considers multi-agent reinforcement learning (MARL) in networked system control. Specifically, each agent learns a decentralized control policy based on local observations and messages from connected neighbors. We formulate such a networked MARL (NMARL) problem as a spatiotemporal Markov decision process and introduce a spatial discount factor to stabilize the training of each local agent. Further, we propose a new differentiable communication protocol, called NeurComm, to reduce information loss and non-stationarity in NMARL. Based on experiments in realistic NMARL scenarios of adaptive traffic signal control and cooperative adaptive cruise control, an appropriate spatial discount factor effectively enhances the learning curves of non-communicative MARL algorithms, while NeurComm outperforms existing communication protocols in both learning efficiency and control performance.

📄 PDF Abstract BibTeX arXiv:2004.01339

Code (1)

cts198859/deeprl_network 공식 구현 tf

Tasks

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Traffic Signal Control

Learning Predictive Communication by Imagination in Networked System Control

2021-01-01 · Yali Du, Yifan Zhao, Meng Fang, Jun Wang 외

Dealing with multi-agent control in networked systems is one of the biggest challenges in Reinforcement Learning (RL) and limited success has been presented compared to recent deep reinforcement learning in single-agent …

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

A game-theoretic analysis of networked system control for common-pool resource management using multi-agent reinforcement learning

2020-10-15 · NeurIPS 2020 12 · Arnu Pretorius, Scott Cameron, Elan van Biljon, Tom Makkink 외

Multi-agent reinforcement learning has recently shown great promise as an approach to networked system control. Arguably, one of the most difficult and important tasks for which large scale networked system control is ap…

Management Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning+1

Enhancing Cyber Resilience of Networked Microgrids using Vertical Federated Reinforcement Learning

2022-12-17 · Sayak Mukherjee, Ramij R. Hossain, YuAn Liu, Wei Du 외

This paper presents a novel federated reinforcement learning (Fed-RL) methodology to enhance the cyber resiliency of networked microgrids. We formulate a resilient reinforcement learning (RL) training setup which (a) gen…

OpenAI Gym reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Deep Reinforcement Learning Based Networked Control with Network Delays for Signal Temporal Logic Specifications

2021-08-03 · Junya Ikemoto, Toshimitsu Ushio

We apply deep reinforcement learning (DRL) to design of a networked controller with network delays to complete a temporal control task that is described by a signal temporal logic (STL) formula. STL is useful to deal wit…

Deep Reinforcement Learning Reinforcement Learning (RL)

Resilient Control of Networked Microgrids using Vertical Federated Reinforcement Learning: Designs and Real-Time Test-Bed Validations

2023-11-21 · Sayak Mukherjee, Ramij R. Hossain, Sheik M. Mohiuddin, YuAn Liu 외

Improving system-level resiliency of networked microgrids is an important aspect with increased population of inverter-based resources (IBRs). This paper (1) presents resilient control design in presence of adversarial c…

OpenAI Gym Reinforcement Learning (RL)