Enhanced DQN Framework for Selecting Actions and Updating Replay Memory Considering Massive Non-Executable Actions

A Deep-Q-Network (DQN) controls a virtual agent as the level of a player using only screenshots as inputs. Replay memory selects a limited number of experience replays according to an arbitrary batch size and updates them using the associated Q-function. Hence, relatively fewer experience replays of...

وصف كامل

التفاصيل البيبلوغرافية
الحاوية / القاعدة:Applied Sciences
المؤلفون الرئيسيون: Bonwoo Gu, Yunsick Sung
التنسيق: مقال
اللغة:الإنجليزية
منشور في: MDPI AG 2021-11-01
الموضوعات:
Gomoku
game artificial intelligence
replay memory
Deep-Q-Network
reinforcement learning
الوصول للمادة أونلاين:https://www.mdpi.com/2076-3417/11/23/11162

الانترنت

https://www.mdpi.com/2076-3417/11/23/11162

مواد مشابهة