| Japanese | English |
25th LSI Design Contests-in Okinawa Design Specification - 3
3. Deep reinforcement learning
Last year, we dealt with the theme of "reinforcement learning," which is one of the typical methods of machine learning.
[Deep Reinforcement Learning (DQN)] is a method that combines deep learning with "Q-learning," which is a famous learning method for reinforcement learning.
The basic learning method is the same as Q-learning, and through trial and error, learn behaviors that give the maximum reward to the agent (subject who performs the action).
Copyright (C) 2021-2022 LSI Design Contest. All Rights Reserved.