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
Agent Modelling under Partial Observability for Deep Reinforcement Learning.
TL;DR: In this paper, an encoder-decoder architecture is used to extract representations about the modelled agents conditioned only on the local observations of the controlled agent, which are used to augment the decision policy.
Posted Content
Independent Reinforcement Learning for Weakly Cooperative Multiagent Traffic Control Problem
TL;DR: In this paper, the adaptive traffic signal control (ATSC) problem is modeled as a multi-agent cooperative game among urban intersections, where intersections cooperate to optimize their common goal.
Posted Content
On the Use and Misuse of Absorbing States in Multi-agent Reinforcement Learning
Andrew Cohen,Ervin Teng,Vincent-Pierre Berges,Ruo-Ping Dong,Hunter Henry,Marwan Mattar,Alexander Zook,Sujoy Ganguly +7 more
TL;DR: In this article, the authors propose a novel architecture for an existing state-of-the-art MARL algorithm which uses attention instead of a fully connected layer with absorbing states, and demonstrate that this novel architecture significantly outperforms the standard architecture on tasks in which agents are created or destroyed within episodes.
Neural-Attentional Architectures for Deep Multi-Agent Reinforcement Learning in Varying Environments
TL;DR: This work proposes new neural architectures for multi-agent relationships at the policy level by using an attentional architecture, obtaining superior results to a full-knowledge, fully-centralized reference solution, and significantly outperforming it when scaling to large numbers of agents.
Proceedings ArticleDOI
Adaptive Average Exploration in Multi-Agent Reinforcement Learning
Garrett Hall,Ken Holladay +1 more
TL;DR: The objective of this research project was to improve Multi-Agent Reinforcement Learning performance in the StarCraft II environment with respect to faster training times, greater stability, and higher win ratios by creating an adaptive action selector the authors call Adaptive Average Exploration, and using experiences previously learned by a neural network via Transfer Learning.
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.