Generating 2D Lego Compatible Puzzles Using Reinforcement Learning
We present a framework that generates a 2D Lego-compatible puzzle layout of greater than thousands pieces of bricks using a reinforcement learning technique. Many existing 2D legorization strategies have limitations in producing a Lego layout, which is composed of more than thousands of pieces. We a...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9165736/ |
| _version_ | 1818934541144817664 |
|---|---|
| author | Cheolseong Park Heekyung Yang Kyungha Min |
| author_facet | Cheolseong Park Heekyung Yang Kyungha Min |
| author_sort | Cheolseong Park |
| collection | DOAJ |
| description | We present a framework that generates a 2D Lego-compatible puzzle layout of greater than thousands pieces of bricks using a reinforcement learning technique. Many existing 2D legorization strategies have limitations in producing a Lego layout, which is composed of more than thousands of pieces. We attack this problem by employing a reinforcement learning technique, which accelerates the progress of various game strategies. We represent the legorization process as a game tree search problem, where each leaf node of the tree corresponds to a Lego layout. The goal of legorization is to find an optimal Lego layout that achieves maximum reward. To efficiently find a leaf node for the maximum reward layout, we reduce the search space using a dueling deep Q-Network (DQN), which is a widely used reinforcement learning model. Our framework is composed of a learning stage and a legorization stage. In the learning stage, we design a dueling DQN model and train this model using three heuristics for legorization strategies. In the legorization stage, we efficiently generate a large-scaled 2D Lego-compatible puzzle layout by reducing the search space using the trained dueling DQN. This approach enables us to produce a puzzle layout of more than a thousand of pieces, which has not been feasible for existing legorization schemes. |
| first_indexed | 2024-12-20T05:05:55Z |
| format | Article |
| id | doaj.art-5cf304b3ed7c437b8837f79fbf58937d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-20T05:05:55Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-5cf304b3ed7c437b8837f79fbf58937d2022-12-21T19:52:24ZengIEEEIEEE Access2169-35362020-01-01818039418041010.1109/ACCESS.2020.30160919165736Generating 2D Lego Compatible Puzzles Using Reinforcement LearningCheolseong Park0https://orcid.org/0000-0002-9761-7546Heekyung Yang1https://orcid.org/0000-0001-5124-5508Kyungha Min2https://orcid.org/0000-0002-5150-2524Department of Computer Science, Sangmyung University, Seoul, South KoreaDivision of SW Convergence, Sangmyung University, Seoul, South KoreaDepartment of Computer Science, Sangmyung University, Seoul, South KoreaWe present a framework that generates a 2D Lego-compatible puzzle layout of greater than thousands pieces of bricks using a reinforcement learning technique. Many existing 2D legorization strategies have limitations in producing a Lego layout, which is composed of more than thousands of pieces. We attack this problem by employing a reinforcement learning technique, which accelerates the progress of various game strategies. We represent the legorization process as a game tree search problem, where each leaf node of the tree corresponds to a Lego layout. The goal of legorization is to find an optimal Lego layout that achieves maximum reward. To efficiently find a leaf node for the maximum reward layout, we reduce the search space using a dueling deep Q-Network (DQN), which is a widely used reinforcement learning model. Our framework is composed of a learning stage and a legorization stage. In the learning stage, we design a dueling DQN model and train this model using three heuristics for legorization strategies. In the legorization stage, we efficiently generate a large-scaled 2D Lego-compatible puzzle layout by reducing the search space using the trained dueling DQN. This approach enables us to produce a puzzle layout of more than a thousand of pieces, which has not been feasible for existing legorization schemes.https://ieeexplore.ieee.org/document/9165736/Legoreinforcement learningdeep Q-networklegorizationheuristic |
| spellingShingle | Cheolseong Park Heekyung Yang Kyungha Min Generating 2D Lego Compatible Puzzles Using Reinforcement Learning IEEE Access Lego reinforcement learning deep Q-network legorization heuristic |
| title | Generating 2D Lego Compatible Puzzles Using Reinforcement Learning |
| title_full | Generating 2D Lego Compatible Puzzles Using Reinforcement Learning |
| title_fullStr | Generating 2D Lego Compatible Puzzles Using Reinforcement Learning |
| title_full_unstemmed | Generating 2D Lego Compatible Puzzles Using Reinforcement Learning |
| title_short | Generating 2D Lego Compatible Puzzles Using Reinforcement Learning |
| title_sort | generating 2d lego compatible puzzles using reinforcement learning |
| topic | Lego reinforcement learning deep Q-network legorization heuristic |
| url | https://ieeexplore.ieee.org/document/9165736/ |
| work_keys_str_mv | AT cheolseongpark generating2dlegocompatiblepuzzlesusingreinforcementlearning AT heekyungyang generating2dlegocompatiblepuzzlesusingreinforcementlearning AT kyunghamin generating2dlegocompatiblepuzzlesusingreinforcementlearning |