A Tensor Network Implementation of Multi Agent Reinforcement Learning
Not on the map. Why?
Abstract (arXiv)
Recently it has been shown that tensor networks (TNs) have the ability to represent the expected return of a single-agent finite Markov decision process (FMDP). The TN represents a distribution model, where all possible trajectories are considered. When extending these ideas to a multi-agent setting, distribution models suffer from the curse of dimensionality: the exponential relation between the number of possible trajectories and the number of agents. The key advantage of using TNs in this setting is that there exists a large number of established optimisation and decomposition techniques that are specific to TNs, that one can apply to ensure the most efficient representation is found. In this report, these methods are used to form a TN that represents the expected return of a multi-agent reinforcement learning (MARL) task. This model is then applied to a 2 agent random walker example, where it was shown that the policy is correctly optimised using a DMRG technique. Finally, I demonstrate the use of an exact decomposition technique, reducing the number of elements in the tensors by 97.5%, without experiencing any loss of information.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 5 of its 49 references that are in the map. First posted on arXiv 8 Jan 2024.
Builds on
5 of 49 references.
References · 5
- 2019Expressive power of tensor-network factorizations for probabilistic modeling, with applications from hidden Markov models to quantum machine learningcited by 55
- 2019TensorNetwork for Machine Learningcited by 29
- 2019TensorNetwork: A Library for Physics and Machine Learningcited by 21
- 2017Compact Neural Networks based on the Multiscale Entanglement Renormalization Ansatzcited by 3
- 2020A Tensor Network Approach to Finite Markov Decision Processescited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Multilinear Tensor Low-Rank Approximation for Policy-Gradient Methods in Reinforcement Learning
- 2025A Tensor Low-Rank Approximation for Value Functions in Multi-Task Reinforcement Learning
- 2019Hybrid Reinforcement Learning with Expert State Sequences
- 2025Combining Local Symmetry Exploitation and Reinforcement Learning for Optimised Probabilistic Inference -- A Work In Progress
- 2022TTOpt: A Maximum Volume Quantized Tensor Train-based Optimization and its Application to Reinforcement Learning
- 2025SPECTra: Scalable Multi-Agent Reinforcement Learning with Permutation-Free Networks
- 2024Tensor Low-rank Approximation of Finite-horizon Value Functions
- 2025Reinforcement Networks: novel framework for collaborative Multi-Agent Reinforcement Learning tasks