| Texto completo | |
| Autor(es): |
Sbrana, Attilio
;
Bizarro Mirisola, Luiz Gustavo
;
Soma, Nei Yoshihiro
;
Lima de Castro, Paulo Andre
Número total de Autores: 4
|
| Tipo de documento: | Artigo Científico |
| Fonte: | ENTERTAINMENT COMPUTING; v. 47, p. 8-pg., 2023-05-29. |
| Resumo | |
This work proposes a deep learning-based agent that solves 10 x 10 board size puzzle games of the NPComplete Akari genre, while learning tabula rasa, that is, never exposed to any rules of the game. A six-model ensemble is trained to form a single solution policy. Lamp placements are chosen sequentially until the final resolution or failure. For the training and testing of the agent, over 3 million games were randomly produced with at least one known solution. The proposed agent solves 98.1% of Akari games that were never shown to it during training, revealing that the agent can learn implicit rules in NP-complete games. These approaches and training procedures proposed can guide future research on tabula rasa neural network agents for solving games or NP-Complete problems. (AU) | |
| Processo FAPESP: | 22/01524-2 - Inteligência artificial em finanças digitais e cryptomercados: desafios e oportunidades |
| Beneficiário: | PAULO ANDRE LIMA DE CASTRO |
| Modalidade de apoio: | Auxílio à Pesquisa - Regular |