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
Learning in Nonzero-Sum Stochastic Games with Potentials
David Mguni,Yutong Wu,Yali Du,Yaodong Yang,Ziyi Wang,Minne Li,Ying Wen,Joel Jennings,Jun Wang +8 more
TL;DR: In this paper, a stochastic potential games (SPGs) with continuous state-action spaces are modeled and a new generation of MARL learners is introduced that can handle nonzero-sum payoff structures and continuous settings.
Proceedings ArticleDOI
MAGNet: Multi-agent Graph Network for Deep Multi-agent Reinforcement Learning.
TL;DR: MAGNet as mentioned in this paper utilizes a relevance graph representation of the environment obtained by a self-attention mechanism, and a message-generation technique to improve the performance of multi-agent reinforcement learning.
Posted Content
Dynamic Dispatching for Large-Scale Heterogeneous Fleet via Multi-agent Deep Reinforcement Learning
TL;DR: A novel Deep Reinforcement Learning approach to solve the dynamic dispatching problem in mining by proposing an experience-sharing Deep Q Network with a novel abstract state/action representation to learn memories from heterogeneous agents altogether and realizes learning in a centralized way.
Posted Content
QOPT: Optimistic Value Function Decentralization for Cooperative Multi-Agent Reinforcement Learning.
TL;DR: This work proposes a novel value-based algorithm for cooperative multi-agent reinforcement learning, based on the "optimistic" training scheme using two action-value estimators with separate roles, which significantly outperform the baselines for the case where non-cooperative behaviors are penalized more aggressively.
Posted Content
Multi-Agent Deep Reinforcement Learning using Attentive Graph Neural Architectures for Real-Time Strategy Games.
TL;DR: In this paper, a categorized state graph attention policy (CSGA-policy) is proposed for real-time strategy game artificial intelligence research, which is based on deep reinforcement learning (MADRL).
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.