HIGHLIGHTS
- What: Share parallels with such models , where the primary objective is to maximize rewards and ultimately secure a victory, necessitating a balanced approach to exploration and exploitation. Through comparative analysis, the study aims to ascertain the most suitable algorithm for decision-making in real-time strategy games. The aim of this algorithm is to maximize total reward and minimize the cumulative regret.
- Who: Yuchen Sun from the School of Ocean and Civil Engineering, Shanghai Jiao Tong University, Shanghai, China have published the research work: Strategic insights from multi-armed bandits: Applications in real-time strategy . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.