Reinforcement Learning
文章平均质量分 88
SaleJuice
不想搞机器学习的嵌入式工程师,不是好算法工程师。
展开
-
【DRL】DQN (Deep Q Network)
DQN (Deep Q Network)AbstractDQN is a pioneering work of deep reinforcement learning in the real sense. DQN is based on Q-Learning and uses a deep network that is good at fitting.Experience ReplayIn Q-learning, we only use the current reward to update t原创 2021-08-20 00:22:31 · 172 阅读 · 0 评论 -
【RL】Q-Learning & SARSA (State-Action-Reward-State-Action)
Q-Learning & SARSA (State-Action-Reward-State-Action)Q-LearningAbstractQ-Learning is one of the most important algorithms in reinforcement learning. Morden reinforcement learning algorithms are mainly the improvement of Q-Learning. Q-Table is the co原创 2021-08-19 10:03:44 · 232 阅读 · 0 评论