A Survey of Reinforcement Learning Informed by Natural Language
A Survey of Reinforcement Learning Informed by Natural Language
复制标题
DOI：
10.24963/ijcai.2019/880
复制
发表时间：
2019-06
期刊：
影响因子：
--
通讯作者：
Jelena Luketina;Nantas Nardelli;Gregory Farquhar;Jakob N. Foerster;Jacob Andreas;Edward Grefenstette;
中科院分区：
文献类型：
--
作者：
Jelena Luketina;Nantas Nardelli;Gregory Farquhar;Jakob N. Foerster;Jacob Andreas;Edward Grefenstette;
为了在现实世界的任务中取得成功，强化学习（RL）需要利用世界的组成，关系和层次结构，并学会将其转移到手头的任务中。语言表征学习的最新进展使得建立从文本语料库中获取世界知识并将这些知识整合到下游决策问题中的模型成为可能。因此，我们认为，现在是时候研究将自然语言理解紧密集成到RL中了。我们调查了该领域的现状，包括指导工作，文本游戏和学习文本领域知识。最后，我们呼吁开发新的环境，并进一步调查最近的自然语言处理（NLP）技术在这些任务中的潜在用途。
To be successful in real-world tasks, Reinforcement Learning (RL) needs to exploit the compositional, relational, and hierarchical structure of the world, and learn to transfer it to the task at hand. Recent advances in representation learning for language make it possible to build models that acquire world knowledge from text corpora and integrate this knowledge into downstream decision making problems. We thus argue that the time is right to investigate a tight integration of natural language understanding into RL in particular. We survey the state of the field, including work on instruction following, text games, and learning from textual domain knowledge. Finally, we call for the development of new environments as well as further investigation into the potential uses of recent Natural Language Processing (NLP) techniques for such tasks.