CubeTR: Learning to Solve the Rubik's Cube using Transformers

2021-09-29 · Mustafa Ebrahim Chasmai

Since its first appearance, transformers have been successfully used in wide ranging domains from computer vision to natural language processing. Application of transformers in Reinforcement Learning by reformulating it as a sequence modelling problem was proposed only recently. Compared to other commonly explored reinforcement learning problems, the Rubik's cube poses a unique set of challenges. The Rubik’s cube has a single solved state for quintillions of possible configurations which leads to extremely sparse rewards. The proposed model CubeTR attends to longer sequences of actions and addresses the problem of sparse rewards. CubeTR learns how to solve the Rubik's cube from arbitrary starting states without any human prior, and after move regularisation, the lengths of solutions generated by it are expected to be very close to those given by algorithms used by expert human solvers. CubeTR provides insights to the generalisability of learning algorithms to higher dimensional cubes and the applicability of transformers in other relevant sparse reward scenarios.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Rubik's Cube

CubeTR: Learning to Solve The Rubiks Cube Using Transformers

2021-11-11 · Mustafa Ebrahim Chasmai

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Towards Learning Rubik's Cube with N-tuple-based Reinforcement Learning

2023-01-28 · Wolfgang Konen

This work describes in detail how to learn and solve the Rubik's cube game (or puzzle) in the General Board Game (GBG) learning and playing framework. We cover the cube sizes 2x2x2 and 3x3x3. We describe in detail the cu…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Rubik's Cube

Sub-Optimal Multi-Phase Path Planning: A Method for Solving Rubik's Revenge

2016-01-20 · Jared Weed

Rubik's Revenge, a 4x4x4 variant of the Rubik's puzzles, remains to date as an unsolved puzzle. That is to say, we do not have a method or successful categorization to optimally solve every one of its approximately $7.40…

Rubik's Cube Time Series Time Series Analysis

Solving Rubik's Cube Without Tricky Sampling

2024-11-29 · Yicheng Lin, Siyu Liang

The Rubiks Cube, with its vast state space and sparse reward structure, presents a significant challenge for reinforcement learning (RL) due to the difficulty of reaching rewarded states. Previous research addressed this…

Policy Gradient Methods Reinforcement Learning (RL)Rubik's Cube

A Machine Learning Approach That Beats Large Rubik's Cubes

2025-02-18 · Alexander Chervov, Kirill Khoruzhii, Nikita Bukhal, Jalal Naghiyev 외

The paper proposes a novel machine learning-based approach to the pathfinding problem on extremely large graphs. This method leverages diffusion distance estimation via a neural network and uses beam search for pathfindi…

Rubik's Cube