Reinforcement learning for Quantum Tiq-Taq-Toe

Catalin-Viorel Dinu, Thomas Moerland
11/10/2024
cs.AI

No official code found. Best implementation: Dinu23/Quantum-Tiq-Taq-Toe (1 star, last commit 2024-08-23).

Abstract

Quantum Tiq-Taq-Toe is a well-known benchmark and playground for both quantum computing and machine learning. Despite its popularity, no reinforcement learning (RL) methods have been applied to Quantum Tiq-Taq-Toe. Although there has been some research on Quantum Chess this game is significantly more complex in terms of computation and analysis. Therefore, we study the combination of quantum computing and reinforcement learning in Quantum Tiq-Taq-Toe, which may serve as an accessible testbed for the integration of both fields. Quantum games are challenging to represent classically due to their inherent partial observability and the potential for exponential state complexity. In Quantum Tiq-Taq-Toe, states are observed through Measurement (a 3x3 matrix of state probabilities) and Move History (a 9x9 matrix of entanglement relations), making strategy complex as each move can collapse the quantum state.

View on arXivView PDF

Code Implementations(1)

Dinu23/Quantum-Tiq-Taq-ToeCommunity100%

Reinforcement learning for Quantum Tiq-Taq-Toe

10Python, Jupyter NotebookJul 15, 20242 years ago

Similar Papers

Reinforcement Learning for Quantum Technology

90% match2026

An Introduction to Quantum Reinforcement Learning (QRL)

90% match2024

Quantum framework for Reinforcement Learning: Integrating Markov decision process, quantum arithmetic, and trajectory search

89% match2024

From Classical Data to Quantum Advantage -- Quantum Policy Evaluation on Quantum Hardware

89% match2025

Reinforcement learning to learn quantum states for Heisenberg scaling accuracy

89% match1 repo42024

A quantum-classical reinforcement learning model to play Atari games

88% match1 repo2024

Cite this paper

@article{dinu2024reinforcement,
  title  = {Reinforcement learning for Quantum Tiq-Taq-Toe},
  author = {Catalin-Viorel Dinu and Thomas Moerland},
  year   = {2024},
  eprint = {2411.06429},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2411.06429v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2411.06429.svg)](https://codeofpaper.com/paper/2411.06429)

Discussion