Optimizing Neural Network Performance in Game Playing Using Simulated Annealing and Reinforcement Learning
Resumo
This paper experiments optimization for Neural Network (NN) parameters for game playing using Simulated Annealing (SA) and Reinforcement Learning (RL). The study focuses on the Dino Game, comparing the performance of the proposed NN method against a baseline Decision Tree method. Experimental results demonstrate that the NN outperforms the Decision Tree, achieving a higher mean score with greater consistency. Statistical tests confirm the performance improvements are statistically significant, indicating the effectiveness of the SA heuristic in optimizing NN parameters.Referências
Boyd, S. and Vandenberghe, L. (2004). Convex Optimization. Cambridge University Press.
Burkard, R. and Rendl, F. (1984). A thermodynamically motivated simulation procedure for combinatorial optimization problems. European Journal of Operational Research, 17(2):169–174.
Černỳ, V. (1985). Thermodynamical approach to the traveling salesman problem: An efficient simulation algorithm. Journal of optimization theory and applications, 45:41–51.
Kirkpatrick, S., Gelatt Jr, C. D., and Vecchi, M. P. (1983). Optimization by simulated annealing. science, 220(4598):671–680.
Kulkarni, A., Bapat, P., Kulkarni, T., and Pawar, R. (2023). Review of reinforcement learning in chrome dino game. In 2023 7th International Conference On Computing, Communication, Control And Automation (ICCUBEA), pages 1–5.
McCulloch, W. S. and Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics, 5(4):115–133.
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., Van Den Driessche, G., Schrit-twieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016). Mastering the game of go with deep neural networks and tree search. nature, 529(7587):484–489.
Sutton, R. S. and Barto, A. G. (2018). Reinforcement learning: An introduction. MIT press.
Van Laarhoven, P. J., Aarts, E. H., van Laarhoven, P. J., and Aarts, E. H. (1987). Simulated annealing. Springer.
Burkard, R. and Rendl, F. (1984). A thermodynamically motivated simulation procedure for combinatorial optimization problems. European Journal of Operational Research, 17(2):169–174.
Černỳ, V. (1985). Thermodynamical approach to the traveling salesman problem: An efficient simulation algorithm. Journal of optimization theory and applications, 45:41–51.
Kirkpatrick, S., Gelatt Jr, C. D., and Vecchi, M. P. (1983). Optimization by simulated annealing. science, 220(4598):671–680.
Kulkarni, A., Bapat, P., Kulkarni, T., and Pawar, R. (2023). Review of reinforcement learning in chrome dino game. In 2023 7th International Conference On Computing, Communication, Control And Automation (ICCUBEA), pages 1–5.
McCulloch, W. S. and Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics, 5(4):115–133.
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., Van Den Driessche, G., Schrit-twieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016). Mastering the game of go with deep neural networks and tree search. nature, 529(7587):484–489.
Sutton, R. S. and Barto, A. G. (2018). Reinforcement learning: An introduction. MIT press.
Van Laarhoven, P. J., Aarts, E. H., van Laarhoven, P. J., and Aarts, E. H. (1987). Simulated annealing. Springer.
Publicado
17/10/2024
Como Citar
LAYBER, Henrique Coutinho; BONELLA, Vitor Berger; VAREJÃO, Flávio Miguel.
Optimizing Neural Network Performance in Game Playing Using Simulated Annealing and Reinforcement Learning. In: ESCOLA REGIONAL DE INFORMÁTICA DO ESPÍRITO SANTO, 9. , 2024, Vitória/ES.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2024
.
p. 177-180.
DOI: https://doi.org/10.5753/eries.2024.244341.
