| 释义 |
1 ?延宕奖赏 ... delayed response learning 延迟反应学习 delayed reward 延宕奖赏 delayed sensation 延缓感觉 ... 2 ?延迟回报 反复实验搜索（trial-and-error search）和延迟回报（delayed reward）是强化学习的两个主要特 征 [2] 。Q-学习是一种典型的强化学习算法 [3] 。
- 1
Delayed reward may be expected from news of public affairs, economic matters, social problems, science, education, and health. 而延迟回报则往往和公众事件、经济、社会问题、科学、教育以及健康等方面的行为有关。 - 2
Participants were asked to make eight choices; each was between receiving a small, but immediate, reward and a larger, but delayed, reward. 参与者被要求作出八项选择，每一项都是在得到一个小的但即时的奖励和一个更大的但延时的奖励之间。 - 3
Saving it for retirement or a rainy day brings together a variety of positive emotions that can lead to happiness, such as anticipation and expectation, a sense of delayed gratification and reward. 为退休，或哪天天有不测而存钱会把各式各样最终能带来快乐的积极情绪聚集到一起，例如，期望和指望，延期的满足感和奖励感。
|