We propose a new deep learning model for goal-driven tasks that require intuitive physical reasoning and intervention in the scene to achieve a desired end goal. Its modular structure is motivated by hypothesizing a sequence of intuitive steps that humans apply when trying to solve such a task. The model first predicts the path the target object would follow without intervention and the path the target object should follow in order to solve the task. Next, it predicts the desired path of the action object and generates the placement of the action object. All components of the model are trained jointly in a supervised way; each component receives its own learning signal but learning signals are also backpropagated through the entire architecture. To evaluate the model we use PHYRE - a benchmark test for goal-driven physical reasoning in 2D mechanics puzzles.
Centro Universitário FEI（FEI大学中心）；University of Corunna（科鲁尼亚大学）
Spatial puzzles composed of rigid objects, flexible strings and holes offer interesting domains for reasoning about spatial entities that are common in the human daily-life's activities. The goal of this work is to investigate the automated solution of this kind of puzzles adapting an algorithm that combines Answer Set Programming (ASP) with Markov Decision Process (MDP), algorithm oASP(MDP), to use heuristics accelerating the learning process. ASP is applied to represent the domain as an MDP, while a Reinforcement Learning algorithm (Q-Learning) is used to find the optimal policies. In this w…
Insight Centre for Data Analytics（洞察数据分析中心）；University College Cork（科克大学学院）
We present in this paper our solver for logic grid puzzles. The approach used by our algorithm mimics the way a human would try to solve the same problem. Every progress made during the solving process is accompanied by a detailed explanation of our program's reasoning. Since this reasoning is based on the same heuristics that a human would employ, the user can easily follow the given explanation.
PeopleTec, Inc.（PeopleTec公司）；University of Maryland, College Park（马里兰大学学院市分校）
The application of Generative Pre-trained Transformer (GPT-2) to learn text-archived game notation provides a model environment for exploring sparse reward gameplay. The transformer architecture proves amenable to training on solved text archives describing mazes, Rubik's Cube, and Sudoku solvers. The method benefits from fine-tuning the transformer architecture to visualize plausible strategies derived outside any guidance from human heuristics or domain expertise. The large search space ($>10^{19}$) for the games provides a puzzle environment in which the solution has few intermediate reward…
The pictorial jigsaw (PJ) puzzle is a well-known leisure game for humans. Usually, a PJ puzzle game is played by one or several human players face-to-face in the physical space. In this paper, we focus on how to solve PJ puzzles in the cyberspace by a group of physically distributed human players. We propose an approach to solving PJ puzzle by stigmergy-inspired Internet-based human collective intelligence. The core of the approach is a continuously executing loop, named the EIF loop, which consists of three activities: exploration, integration, and feedback. In exploration, each player tries …
Centre de Recherche en Informatique de Lens（朗斯计算机研究中心）；Université d’Artois（阿尔图瓦大学）；Maastricht University（马斯特里赫特大学）
Many of the famous single-player games, commonly called puzzles, can be shown to be NP-Complete. Indeed, this class of complexity contains hundreds of puzzles, since people particularly appreciate completing an intractable puzzle, such as Sudoku, but also enjoy the ability to check their solution easily once it's done. For this reason, using constraint programming is naturally suited to solve them. In this paper, we focus on logic puzzles described in the Ludii general game system and we propose using the XCSP formalism in order to solve them with any CSP solver.
Puzzle Solving using Reasoning of Large Language Models: A Survey
Artificial Intelligence and Learning Systems Laboratory（人工智能与学习系统实验室）；School of Electrical and Computer Engineering（电气与计算机工程学院）；National Technical University of Athens（希腊雅典国家技术大学）
Understanding and reasoning about physics is an important ability of intelligent agents. We develop the PHYRE benchmark for physical reasoning that contains a set of simple classical mechanics puzzles in a 2D physical environment. The benchmark is designed to encourage the development of learning algorithms that are sample-efficient and generalize well across puzzles. We test several modern learning algorithms on PHYRE and find that these algorithms fall short in solving the puzzles efficiently. We expect that PHYRE will encourage the development of novel sample-efficient agents that learn eff…
Solving crossword puzzles requires diverse reasoning capabilities, access to a vast amount of knowledge about language and the world, and the ability to satisfy the constraints imposed by the structure of the puzzle. In this work, we introduce solving crossword puzzles as a new natural language understanding task. We release the specification of a corpus of crossword puzzles collected from the New York Times daily crossword spanning 25 years and comprised of a total of around nine thousand puzzles. These puzzles include a diverse set of clues: historic, factual, word meaning, synonyms/antonyms…
National Institute of Informatics（国立信息学研究所）；Keio University（庆应义塾大学）
A sliding puzzle is a combination puzzle where a player slide pieces along certain routes on a board to reach a certain end-configuration. In this paper, we propose a novel measurement of complexity of massive sliding puzzles with paramodulation which is an inference method of automated reasoning. It turned out that by counting the number of clauses yielded with paramodulation, we can evaluate the difficulty of each puzzle. In experiment, we have generated 100 * 8 puzzles which passed the solvability checking by countering inversions. By doing this, we can distinguish the complexity of 8 puzzl…
The Keke AI Competition introduces an artificial agent competition for the game Baba is You - a Sokoban-like puzzle game where players can create rules that influence the mechanics of the game. Altering a rule can cause temporary or permanent effects for the rest of the level that could be part of the solution space. The nature of these dynamic rules and the deterministic aspect of the game creates a challenge for AI to adapt to a variety of mechanic combinations in order to solve a level. This paper describes the framework and evaluation metrics used to rank submitted agents and baseline resu…
Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad?
AIML Lab, TU Darmstadt（AIML实验室，德累斯顿技术大学）；Hessian Center for AI (hessian.ai)（黑森人工智能中心）；Institute of Psychology, TU Darmstadt（心理学研究所，德累斯顿技术大学）；Centre for Cognitive Science, TU Darmstadt（认知科学中心，德累斯顿技术大学）；German Center for AI (DFKI)（德国人工智能中心）
Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles
ByteDance Seed（字节跳动种子）；Fudan University（复旦大学）；Institute for AI Industry Research (AIR), Tsinghua University（人工智能产业研究院（AIR），清华大学）；Nanjing University（南京大学）；Shanghai Jiao Tong University（上海交通大学）；SIA-Lab of Tsinghua AIR and ByteDance Seed（清华大学AIR实验室和字节跳动种子）
Charles University（查理大学）；Accenture Central Europe B.V.（埃森哲中欧有限公司）
The problem of solving $(n^2-1)$-puzzle and cooperative path-finding (CPF) sub-optimally by rule based algorithms is addressed in this manuscript. The task in the puzzle is to rearrange $n^2-1$ pebbles on the square grid of the size of n x n using one vacant position to a desired goal configuration. An improvement to the existent polynomial-time algorithm is proposed and experimentally analyzed. The improved algorithm is trying to move pebbles in a more efficient way than the original algorithm by grouping them into so-called snakes and moving them jointly within the snake. An experimental eva…
JigShape: Evaluating Visual-Geometric Reasoning in VLMs through Jigsaw Puzzles
University of Southern California（南加州大学）；National University of Singapore（新加坡国立大学）；Adobe Research（奥多比研究院）；Texas A&M University（德克萨斯农工大学）；Rice University（莱斯大学）；The University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
