Solving Twisty Puzzles Using Parallel Q-learning

Hukmani, Kavish and Kolekar, Sucheta and Vobugari, Sreekumar (2021) Solving Twisty Puzzles Using Parallel Q-learning. Engineering Letters, 29 (4). ISSN 1816-093X

[img] PDF
13837.pdf - Published Version
Restricted to Registered users only

Download (10MB) | Request a copy


There has been a recent trend of teaching agents to solve puzzles and play games using Deep Reinforcement Learn�ing (DRL) which was brought by the success of AlphaGo. While this method has given some truly groundbreaking results and it is very computationally intensive. This paper evaluates the feasibility of solving Combinatorial Optimization Problems such as Twisty Puzzles using Parallel Q-Learning (PQL). We propose a method using Constant Share-Reinforcement Learning (CS�RL) as a more resource optimized approach and measure the impact of sub- goals built using human knowledge. We attempt to solve three puzzles, the 2x2x2 Pocket Rubik’s Cube, the Skewb and the Pyraminx with and without sub-goals based on popular solving methods used by humans and compare their results. Our agents are able to solve these puzzles with a 100% success rate by just a few hours of training, much better than previous DRL based agents that require large computational time. Further, the proposed approach is compared with Deep Learning based solution for 2x2x2 Rubik’s Cube and observed higher success rate

Item Type: Article
Uncontrolled Keywords: —Parallel Programming ; Q-learning ; Rein�forcement Learning ; Twisty Puzzles ; Rubik’s Cube ; Agent�based Programming
Subjects: Engineering > MIT Manipal > Information and Communication Technology
Depositing User: MIT Library
Date Deposited: 23 Mar 2022 09:17
Last Modified: 23 Mar 2022 09:17

Actions (login required)

View Item View Item