mlsanityData to 7 Oct 2026

Model based Multi-agent Reinforcement Learning with Tensor Decompositions

arXiv 2110.14524 ↗First posted 27 Oct 2021cs.LG cs.MAcited by 7

Not on the map. Why?

Abstract (arXiv)

A challenge in multi-agent reinforcement learning is to be able to generalize over intractable state-action spaces. Inspired from Tesseract [Mahajan et al., 2021], this position paper investigates generalisation in state-action space over unexplored state-action pairs by modelling the transition and reward functions as tensors of low CP-rank. Initial experiments on synthetic MDPs show that using tensor decompositions in a model-based reinforcement learning algorithm can lead to much faster convergence if the true transition and reward functions are indeed of low rank.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 16 of its 23 references that are in the map. First posted on arXiv 27 Oct 2021.

Builds on

16 of 23 references.

References · 16

  1. 2018QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 697
  2. 2017A Survey of Model Compression and Acceleration for Deep Neural Networkscited by 298
  3. 2020QPLEX: Duplex Dueling Multi-Agent Q-Learningcited by 267
  4. 2019MAVEN: Multi-Agent Variational Explorationcited by 181
  5. 2021Open-Ended Learning Leads to Generally Capable Agentscited by 177
  6. 2020RODE: Learning Roles to Decompose Multi-Agent Taskscited by 125
  7. 2017Tensor Networks for Dimensionality Reduction and Large-Scale Optimizations. Part 2 Applications and Future Perspectivescited by 53
  8. 2016Reinforcement Learning of POMDPs using Spectral Methodscited by 51
  9. 2019Factorized Higher-Order CNNs with an Application to Spatio-Temporal Emotion Estimationcited by 40
  10. 2020UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learningcited by 32
  11. 2014Provable Tensor Factorization with Missing Datacited by 31
  12. 2021Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learningcited by 25
4 more
  1. 2019T-Net: Parametrizing Fully Convolutional Nets with a Single High-Order Tensorcited by 22
  2. 2014Guaranteed Non-Orthogonal Tensor Decomposition via Alternating Rank-1 Updatescited by 21
  3. 2019Incremental multi-domain learning with network latent tensor factorizationcited by 16
  4. 2020Tensor Completion Made Practicalcited by 15

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 1; 2024: 0; 2025: 2.

7 papers.

  1. 2022Model-based Multi-agent Reinforcement Learning: Recent Progress and Prospectscited by 17
  2. 2022Tensor and Matrix Low-Rank Value-Function Approximation in Reinforcement Learningcited by 16
  3. 2022Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium Computationcited by 14
  4. 2022Interaction Pattern Disentangling for Multi-Agent Reinforcement Learningcited by 8
  5. 2023Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challengescited by 5
  6. 2025Combining Bayesian Inference and Reinforcement Learning for Agent Decision Making: A Reviewcited by 1
  7. 2025Multi-Robot Collaboration through Reinforcement Learning and Abstract Simulationcited by 0