Weighted QMIX: Expanding monotonic value function factorisation for deep multi−agent reinforcement learning

Weighted QMIX: Expanding monotonic value function factorisation for deep multi−agent reinforcement learning

QMIX is a popular Q-learning algorithm for cooperative MARL in the centralised training and decentralised execution paradigm. In order to enable easy decentralisation, QMIX restricts the joint action Q-values it can represent to be a monotonic mixing of each agent’s utilities. However, this restrict...

Descrizione completa

Dettagli Bibliografici
Autori principali:	Rashid, T, Farquhar, G, Peng, B, Whiteson, S
Natura:	Conference item
Lingua:	English
Pubblicazione:	NeurIPS 2020

Documenti analoghi

QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning
di: Rashid, T, et al.
Pubblicazione: (2018)

Monotonic value function factorisation for deep multi-agent reinforcement learning
di: Rashid, T, et al.
Pubblicazione: (2020)

Exploration and value function factorisation in single and multi-agent reinforcement learning
di: Rashid, T
Pubblicazione: (2021)

Stabilising experience replay for deep multi-agent reinforcement learning
di: Foerster, J, et al.
Pubblicazione: (2017)

Bayesian action decoder for deep multi-agent reinforcement learning
di: Whiteson, S
Pubblicazione: (2019)

UneVEn: Universal value exploration for multi-agent reinforcement learning
di: Gupta, T, et al.
Pubblicazione: (2021)

Learning to communicate with Deep multi-agent reinforcement learning
di: Foerster, J, et al.
Pubblicazione: (2016)

Multi-agent common knowledge reinforcement learning
di: de Witt, C, et al.
Pubblicazione: (2019)

Regularized Softmax Deep Multi−Agent Q−Learning
di: Pan, L, et al.
Pubblicazione: (2022)

Analysing factorizations of action-value networks for cooperative multi-agent reinforcement learning
di: Castellini, J, et al.
Pubblicazione: (2021)

Deep reinforcement learning to multi-agent deep reinforcement learning
di: Samieiyeganeh, Mehdi, et al.
Pubblicazione: (2022)

Deep multi-agent reinforcement learning
di: Foerster, J
Pubblicazione: (2018)

Counterfactual multi−agent policy gradients
di: Foerster, J, et al.
Pubblicazione: (2018)

QMix: A Python package for simulating the quasiparticle tunneling currents in SIS junctions
di: Garrett, J, et al.
Pubblicazione: (2019)

TreeQN and ATreeC: differentiable tree planning for deep reinforcement learning
di: Farquhar, G, et al.
Pubblicazione: (2018)

Transient non−stationarity and generalisation in deep reinforcement learning
di: Igl, M, et al.
Pubblicazione: (2021)

Randomized entity-wise factorization for multi-agent reinforcement learning
di: Iqbal, S, et al.
Pubblicazione: (2021)

On Factorisation of Provenance Polynomials
di: Olteanu, D, et al.
Pubblicazione: (2011)

Factorisation in relational databases
di: Zavodny, J
Pubblicazione: (2014)

Coordination and communication in deep multi-agent reinforcement learning
di: Schroeder de Witt, CA
Pubblicazione: (2021)

Loading monotonicity of weighted premiums, and total positivity properties of weight functions
di: Richards, Donald, et al.
Pubblicazione: (2021)

From matrix factorisation to signal propagation in deep learning: algorithms and guarantees
di: Murray, M
Pubblicazione: (2021)

Factorising Proofs in Timed CSP
di: Davies, J, et al.
Pubblicazione: (1989)

Pushing forward matrix factorisations
di: Dyckerhoff, T, et al.
Pubblicazione: (2011)

Improving single and multi-agent deep reinforcement learning methods
di: Gupta, T
Pubblicazione: (2023)

MAVEN: Multi-Agent Variational Exploration
di: Mahajan, A, et al.
Pubblicazione: (2019)

Efficient and scalable methods for deep reinforcement learning
di: Farquhar, G
Pubblicazione: (2020)

Tesseract: tensorised actors for multi−agent reinforcement learning
di: Mahajan, A, et al.
Pubblicazione: (2021)

The value of information in monotone decixion problems
di: Athey, Susan, et al.
Pubblicazione: (2011)

Deep residual reinforcement learning
di: Zhang, S, et al.
Pubblicazione: (2020)

End-to-end deep reinforcement learning for multi-agent collaborative exploration
di: Chen, Zichen, et al.
Pubblicazione: (2021)

Multi-agent deep reinforcement learning for mix-mode runway sequencing
di: Shi, Limin, et al.
Pubblicazione: (2022)

The StarCraft Multi-Agent Challenge
di: Mikayel Samvelyan, et al.
Pubblicazione: (2019)

Deep decentralized multi-task multi-agent reinforcement learning under partial observability
di: How, Jonathan
Pubblicazione: (2021)

Factorisation of greedoid polynomials of rooted digraphs
di: Yow, Kai Siong, et al.
Pubblicazione: (2021)

The antitriangular factorisation of saddle point matrices
di: Pestana, J, et al.
Pubblicazione: (2013)

Monotone Equilibrium in Multi-Unit Auctions
di: McAdams, David
Pubblicazione: (2002)

Loaded DiCE: Trading off bias and variance in any-order score function gradient estimators for reinforcement learning
di: Farquhar, G, et al.
Pubblicazione: (2019)

Multi-agent deep reinforcement learning based multi-timescale voltage control for distribution system
di: Wang, Bingyu
Pubblicazione: (2022)

Forward jets in high energy factorisation at the lhc
di: Deák, M, et al.
Pubblicazione: (2009)