mlsanityData to 7 Oct 2026

Alphazzle: Jigsaw Puzzle Solver with Deep Monte-Carlo Tree Search

arXiv 2302.00384 ↗First posted 1 Feb 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Solving jigsaw puzzles requires to grasp the visual features of a sequence of patches and to explore efficiently a solution space that grows exponentially with the sequence length. Therefore, visual deep reinforcement learning (DRL) should answer this problem more efficiently than optimization solvers coupled with neural networks. Based on this assumption, we introduce Alphazzle, a reassembly algorithm based on single-player Monte Carlo Tree Search (MCTS). A major difference with DRL algorithms lies in the unavailability of game reward for MCTS, and we show how to estimate it from the visual input with neural networks. This constraint is induced by the puzzle-solving task and dramatically adds to the task complexity (and interest!). We perform an in-deep ablation study that shows the importance of MCTS and the neural networks working together. We achieve excellent results and get exciting insights into the combination of DRL and visual feature learning.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 42 references that are in the map. First posted on arXiv 1 Feb 2023.

Builds on

16 of 42 references.

References · 16

  1. 2016Wide Residual Networkscited by 3,057
  2. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  3. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
  4. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
  5. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 723
  6. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 449
  7. 2017Thinking Fast and Slow with Deep Learning and Tree Searchcited by 245
  8. 2018Boosting Self-Supervised Learning via Knowledge Transfercited by 92
  9. 2018Learning Image Representations by Completing Damaged Jigsaw Puzzlescited by 66
  10. 2018Iterative Reorganization with Weak Spatial Constraints: Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation Learningcited by 51
  11. 2018Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimizationcited by 25
  12. 2018Single-Agent Policy Tree Search With Guaranteescited by 22
4 more
  1. 2020Deepzzle: Solving Visual Jigsaw Puzzles with Deep Learning andShortest Path Optimizationcited by 19
  2. 2019Solving Jigsaw Puzzles with Eroded Boundariescited by 13
  3. 2018Image Reassembly Combining Deep Learning and Shortest Path Problemcited by 7
  4. 2020Single-Agent Optimization Through Policy Iteration Using Monte-Carlo Tree Searchcited by 3

Built on by

Not cited yet.