Graph Convolutional Reinforcement Learning

2018-10-22 · ICLR 2020 1 · Jiechuan Jiang, Chen Dun, Tiejun Huang, Zongqing Lu

Learning to cooperate is crucially important in multi-agent environments. The key is to understand the mutual interplay between agents. However, multi-agent environments are highly dynamic, where agents keep moving and their neighbors change quickly. This makes it hard to learn abstract representations of mutual interplay between agents. To tackle these difficulties, we propose graph convolutional reinforcement learning, where graph convolution adapts to the dynamics of the underlying graph of the multi-agent environment, and relation kernels capture the interplay between agents by their relation representations. Latent features produced by convolutional layers from gradually increased receptive fields are exploited to learn cooperation, and cooperation is further improved by temporal relation regularization for consistency. Empirically, we show that our method substantially outperforms existing methods in a variety of cooperative scenarios.

📄 PDF Abstract BibTeX arXiv:1810.09202

Code (4)

PKU-AI-Edge/DGN 공식 구현 tf

PKU-AI-Edge/DGN/ 공식 구현 tf

jiechuanjiang/pytorch_dgn pytorch

pku-rl/dgn tf

Tasks

Decision Making reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Relation

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Graph Convolutional Memory using Topological Priors

2021-06-27 · Steven D. Morad, Stephan Liwicki, Ryan Kortvelesy, Roberto Mecca 외

Solving partially-observable Markov decision processes (POMDPs) is critical when applying reinforcement learning to real-world problems, where agents have an incomplete view of the world. We present graph convolutional m…

Memorization reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Reinforcement Learning for Scalable Logic Optimization with Graph Neural Networks

2021-05-04 · Xavier Timoneda, Lukas Cavigelli

Logic optimization is an NP-hard problem commonly approached through hand-engineered heuristics. We propose to combine graph convolutional networks with reinforcement learning and a novel, scalable node embedding method …

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Deep Graph Convolutional Reinforcement Learning for Financial Portfolio Management -- DeepPocket

2021-05-06 · Farzan Soleymani, Eric Paquet

Portfolio management aims at maximizing the return on investment while minimizing risk by continuously reallocating the assets forming the portfolio. These assets are not independent but correlated during a short time pe…

Management reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Deep Reinforcement Learning-Based Channel Allocation for Wireless LANs with Graph Convolutional Networks

2019-05-17 · Kota Nakashima, Shotaro Kamiya, Kazuki Ohtsu, Koji Yamamoto 외

Last year, IEEE 802.11 Extremely High Throughput Study Group (EHT Study Group) was established to initiate discussions on new IEEE 802.11 features. Coordinated control methods of the access points (APs) in the wireless l…

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

Spatio-Temporal Graph Convolutional Neural Networks for Physics-Aware Grid Learning Algorithms

2022-03-31 · Tong Wu, Ignacio Losada Carreno, Anna Scaglione, Daniel Arnold

This paper proposes a model-free Volt-VAR control (VVC) algorithm via the spatio-temporal graph ConvNet-based deep reinforcement learning (STGCN-DRL) framework, whose goal is to control smart inverters in an unbalanced d…