FDQN: A Flexible Deep Q-Network Framework for Game Automation
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909212696641536 |
|---|---|
| author | Gujavarthy, Prabhath Reddy |
| author_facet | Gujavarthy, Prabhath Reddy |
| contents | In reinforcement learning, it is often difficult to automate high-dimensional, rapid decision-making in dynamic environments, especially when domains require real-time online interaction and adaptive strategies such as web-based games. This work proposes a state-of-the-art Flexible Deep Q-Network (FDQN) framework that can address this challenge with a selfadaptive approach that is processing high-dimensional sensory data in realtime using a CNN and dynamically adapting the model architecture to varying action spaces of different gaming environments and outperforming previous baseline models in various Atari games and the Chrome Dino game as baselines. Using the epsilon-greedy policy, it effectively balances the new learning and exploitation for improved performance, and it has been designed with a modular structure that it can be easily adapted to other HTML-based games without touching the core part of the framework. It is demonstrated that the FDQN framework can successfully solve a well-defined task in a laboratory condition, but more importantly it also discusses potential applications to more challenging real-world cases and serve as the starting point for future further exploration into automated game play and beyond. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_18761 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FDQN: A Flexible Deep Q-Network Framework for Game Automation Gujavarthy, Prabhath Reddy Machine Learning 68T05, 93E35 I.2.8; I.2.6; I.5.1 In reinforcement learning, it is often difficult to automate high-dimensional, rapid decision-making in dynamic environments, especially when domains require real-time online interaction and adaptive strategies such as web-based games. This work proposes a state-of-the-art Flexible Deep Q-Network (FDQN) framework that can address this challenge with a selfadaptive approach that is processing high-dimensional sensory data in realtime using a CNN and dynamically adapting the model architecture to varying action spaces of different gaming environments and outperforming previous baseline models in various Atari games and the Chrome Dino game as baselines. Using the epsilon-greedy policy, it effectively balances the new learning and exploitation for improved performance, and it has been designed with a modular structure that it can be easily adapted to other HTML-based games without touching the core part of the framework. It is demonstrated that the FDQN framework can successfully solve a well-defined task in a laboratory condition, but more importantly it also discusses potential applications to more challenging real-world cases and serve as the starting point for future further exploration into automated game play and beyond. |
| title | FDQN: A Flexible Deep Q-Network Framework for Game Automation |
| topic | Machine Learning 68T05, 93E35 I.2.8; I.2.6; I.5.1 |
| url | https://arxiv.org/abs/2405.18761 |