Situated Mapping of Sequential Instructions to Actions with Single-step Reward Observation
Situated Mapping of Sequential Instructions to Actions with Single-step Reward Observation
复制标题
DOI：
10.18653/v1/p18-1193
复制
发表时间：
2018-05
期刊：
影响因子：
--
通讯作者：
Alane Suhr;Yoav Artzi
中科院分区：
文献类型：
--
作者：
Alane Suhr;Yoav Artzi
我们提出了一种学习方法，将与上下文相关的顺序指令映射到动作。我们使用基于注意力的模型来解决话语和状态依赖性问题，该模型既考虑互动的历史和世界状态。为了从开始和目标状态训练而无需参加示威活动，我们提出了Sestra，这是一种学习算法，利用单步奖励观察和立即预期的奖励最大化。我们对Scone域进行评估，并在使用高级逻辑表示的方法上显示了9.8％-25.3％的绝对精度提高。
We propose a learning approach for mapping context-dependent sequential instructions to actions. We address the problem of discourse and state dependencies with an attention-based model that considers both the history of the interaction and the state of the world. To train from start and goal states without access to demonstrations, we propose SESTRA, a learning algorithm that takes advantage of single-step reward observations and immediate expected reward maximization. We evaluate on the SCONE domains, and show absolute accuracy improvements of 9.8%-25.3% across the domains over approaches that use high-level logical representations.