graphs-2

Rubik's Cube

3260 papers • 126 benchmarks • 313 datasets

Solving the Rubik's Cube is a pathfinding task on a massive implicit graph.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in rubiks-cube-2

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find rubiks-cube-2 models and implementations

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Solving the Rubik's Cube Without Human Knowledge

P. Baldi, Forest Agostinelli, A. Shmakov, S. McAleer•Thu May 17 2018

This work introduces Autodidactic Iteration: a novel reinforcement learning algorithm that is able to teach itself how to solve the Rubik's Cube with no human assistance.

43

Content

0

Paper Graph

Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets

Kai Han, Yunhe Wang, Chunjing Xu, Wei Zhang, Qiulin Zhang, Tong Zhang•Tue Oct 27 2020

A tiny formula for downsizing neural architectures through a series of smaller models derived from the EfficientNet-B0 with the FLOPs constraint is summarized, observing that resolution and depth are more important than width for tiny networks.

99 0

Paper Graph

A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups

A. Wilson, M. Welling, Marc Finzi•Sun Apr 18 2021

This work provides a completely general algorithm for solving for the equivariant layers of matrix groups, and constructs multilayer perceptrons equivariants to multiple groups that have never been tackled before.

219 0

Paper Graph

Solving Rubik's Cube with a Robot Hand

Jonas Schneider, Wojciech Zaremba, A. Paino, Matthias Plappert, Jerry Tworek, Qiming Yuan, Peter Welinder, Bob McGrew, Ma-teusz Litwin, Marcin Andrychowicz, Glenn Powell, Maciek Chociej, Ilge Akkaya, N. Tezak, Lilian Weng, OpenAI, Arthur Petron, Raphael Ribas, Lei M. Zhang•Tue Oct 15 2019

It is demonstrated that models trained only in simulation can be used to solve a manipulation problem of unprecedented complexity on a real robot, made possible by a novel algorithm, which is called automatic domain randomization (ADR), and a robot platform built for machine learning.

1392 0

Paper Graph

Color Recognition for Rubik's Cube Robot

Sheng-lan Liu, Dong Jiang, Lin Feng, Feilong Wang, Zhanbo Feng, Xiang Liu, Shuai Guo, Bingjun Li, Yuchen Cong•Thu Jan 10 2019

A Rubik's cube robot is designed and a dataset is constructed to illustrate the efficiency and effectiveness of the online methods and to indicate the ineffectiveness of offline method by color drifting in the dataset.

6 0

Paper Graph

Projection Path Explorer: Exploring Visual Patterns in Projected Decision-making Paths

A. Hinterreiter, C. Steinparz, Moritz Schofl, Holger Stitz, M. Streit•Sun Jan 19 2020

It is argued that general statements about the problem-solving tasks and solving strategies can be made by interpreting patterns emerging from drawing many trajectories—for different initial conditions, end states, and solution strategies—in the same embedding space.

18 0

Paper Graph

Self-Supervision is All You Need for Solving Rubik's Cube

Kyo Takano•Sat Jun 05 2021

This work introduces a simple and efficient deep learning method for solving combinatorial problems with a predefined goal, represented by Rubik's Cube, and demonstrates that, for such problems, training a deep neural network on random scrambles branching from the goal state is sufficient to achieve near-optimal solutions.

4 0

Paper Graph

Subgoal Search For Complex Reasoning Tasks

Yuhuai Wu, K. Czechowski, Lukasz Kuci'nski, Piotr Milo's, Tomasz Odrzyg'o'zd'z, Marek Zbysi'nski, Michał Zawalski, Krzysztof Olejnik•Tue Aug 24 2021

It is shown that a simple approach of generating $k$-th step ahead subgoals is surprisingly efficient on three challenging domains: two popular puzzle games, Sokoban and the Rubik's Cube, and an inequality proving benchmark INT.

39 0

Paper Graph

AlphaZero-Inspired Game Learning: Faster Training by Using MCTS Only at Test Time

Johann Scheiermann, W. Konen•Wed Apr 27 2022

An important element of AlphaZero—the Monte Carlo Tree Search (MCTS) planning stage—is picked and combined with temporal difference (TD) learning agents to create versatile agents that keep at the same time the computational demands low.

10 0

Paper Graph

Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search

Yuhuai Wu, K. Czechowski, Tomasz Odrzyg'o'zd'z, Michał Zawalski, Michał Tyrolski, Damian Stachura, Piotr Pikekos, Lukasz Kuci'nski, Piotr Milo's•Tue May 31 2022

Adaptive Subgoal Search (AdaSubS), a search method that adaptively adjusts the planning horizon, significantly surpasses hierarchical planning algorithms on three complex reasoning tasks: Sokoban, the Rubik's Cube and inequality proving benchmark INT.

13 0

Paper Graph

Adding a benchmark result helps the community track progress.