Open AccessProceedings Article
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
Tabish Rashid,Mikayel Samvelyan,Christian Schroeder,Gregory Farquhar,Jakob Foerster,Shimon Whiteson +5 more
- pp 4292-4301
TLDR
QMIX employs a network that estimates joint action-values as a complex non-linear combination of per-agent values that condition only on local observations, and structurally enforce that the joint-action value is monotonic in the per- agent values, which allows tractable maximisation of the jointaction-value in off-policy learning.About:
This article is published in International Conference on Machine Learning.The article was published on 2018-07-03 and is currently open access. It has received 505 citations till now. The article focuses on the topics: Reinforcement learning & Monotonic function.read more
Citations
More filters
Posted Content
Signal Instructed Coordination in Cooperative Multi-agent Reinforcement Learning
Liheng Chen,Hongyi Guo,Yali Du,Fei Fang,Haifeng Zhang,Yaoming Zhu,Ming Zhou,Weinan Zhang,Qing Wang,Yong Yu +9 more
TL;DR: To encourage agents to learn to exploit the coordination signal, Signal Instructed Coordination (SIC), a novel coordination module that can be integrated with most existing MARL frameworks is proposed, and shows that SIC consistently improves performance over well-recognized MARL models in both matrix games and a predator-prey game with high-dimensional strategy space.
Posted Content
Correcting Experience Replay for Multi-Agent Communication
Sanjeevan Ahilan,Peter Dayan +1 more
TL;DR: A 'communication correction' is introduced which accounts for the non-stationarity of observed communication induced by multi-agent learning and substantially improves the ability of communicating MARL systems to learn across a variety of cooperative and competitive tasks.
Proceedings ArticleDOI
VarLenMARL: A Framework of Variable-Length Time-Step Multi-Agent Reinforcement Learning for Cooperative Charging in Sensor Networks
TL;DR: In this paper, the authors proposed a new multi-agent reinforcement learning (MARL) framework, called VarLenMARL, which allows each mobile charger to complete an action within a variable length before estimating rewards.
Posted Content
A New Framework for Multi-Agent Reinforcement Learning -- Centralized Training and Exploration with Decentralized Execution via Policy Distillation
TL;DR: In this article, the authors propose a new framework known as centralized training and exploration with decentralized execution via policy distillation, which first trains agents' policies with shared global component to foster coordinated and effective learning.
Proceedings ArticleDOI
AVD-Net: Attention Value Decomposition Network For Deep Multi-Agent Reinforcement Learning
Yuanxin Zhang,Huimin Ma,Yu Wang +2 more
TL;DR: In this article, an attention-based approach called attention value decomposition network (AVD-Net) is proposed, which employs centralized training with decentralized execution paradigm, which factorizes the joint action-value functions with only local observations and actions of agents.
References
More filters
Journal ArticleDOI
Long short-term memory
TL;DR: A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Journal ArticleDOI
Human-level control through deep reinforcement learning
Volodymyr Mnih,Koray Kavukcuoglu,David Silver,Andrei Rusu,Joel Veness,Marc G. Bellemare,Alex Graves,Martin Riedmiller,Andreas K. Fidjeland,Georg Ostrovski,Stig Petersen,Charles Beattie,Amir Sadik,Ioannis Antonoglou,Helen King,Dharshan Kumaran,Daan Wierstra,Shane Legg,Demis Hassabis +18 more
TL;DR: This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.
Posted Content
Empirical evaluation of gated recurrent neural networks on sequence modeling
TL;DR: These advanced recurrent units that implement a gating mechanism, such as a long short-term memory (LSTM) unit and a recently proposed gated recurrent unit (GRU), are found to be comparable to LSTM.
Deep reinforcement learning with double Q-learning
TL;DR: In this article, the authors show that the DQN algorithm suffers from substantial overestimation in some games in the Atari 2600 domain, and they propose a specific adaptation to the algorithm and show that this algorithm not only reduces the observed overestimations, but also leads to much better performance on several games.
Journal ArticleDOI
Learning from delayed rewards
TL;DR: The invention relates to a circuit for use in a receiver which can receive two-tone/stereo signals which is intended to make a choice between mono or stereo reproduction of signal A or of signal B and vice versa.