AI Game Agents Based on Evolutionary Search and (Deep) Reinforcement Learning: A Practical Analysis with Flappy Bird - Entertainment Computing – ICEC 2021 Access content directly
Conference Papers Year : 2021

AI Game Agents Based on Evolutionary Search and (Deep) Reinforcement Learning: A Practical Analysis with Flappy Bird

Abstract

Game agents are efficiently implemented through different AI techniques, such as neural network, reinforcement learning, and evolutionary search. Although there are many works for each approach, we present a critical analysis and comparison between them, suggesting a common benchmark and parameter configurations. The evolutionary strategy implements the NeuroEvolution of Augmenting Topologies algorithm, while the reinforcement learning agent leverages Q-Learning and Proximal Policy Optimization. We formulate and empirically compare this set of solutions using the Flappy Bird game as a test scenario. We also compare different representations of state and reward functions for each method. All methods were able to generate agents that can play the game, where the NEAT algorithm had the best results, reaching the goal of never losing.
Fichier principal
Vignette du fichier
519688_1_En_15_Chapter.pdf (682.19 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04144391 , version 1 (28-06-2023)

Licence

Attribution

Identifiers

Cite

Leonardo Thurler, José Montes, Rodrigo Veloso, Aline Paes, Esteban Clua. AI Game Agents Based on Evolutionary Search and (Deep) Reinforcement Learning: A Practical Analysis with Flappy Bird. 20th International Conference on Entertainment Computing (ICEC), Nov 2021, Coimbra, Portugal. pp.196-208, ⟨10.1007/978-3-030-89394-1_15⟩. ⟨hal-04144391⟩
11 View
5 Download

Altmetric

Share

Gmail Facebook X LinkedIn More