本文介绍了一种基于生成模型的序列预测方法，该方法将模型视为一个与外部环境交互的智能体，通过不断选择行动（预测下一个词）并更新其内部状态来完成序列生成任务。在每个时间步，智能体根据输入的单词和上下文向量采取行动，并在序列结束时获得奖励。
1. Our generative model can be viewed as an agent, which interacts with the external environment (the words and the context vector it sees as input at every time step).
2. The parameters of this agent defines a policy, whose execution results in the agent picking an action.
3. In the sequence generation setting, an action refers to predicting the next word in the sequence at each time step.
4. After taking an action the agent updates its internal state (the hidden units of RNN).
5. Once the agent has reached the end of sequence, it observes a reward.
扫一扫
2404
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
