paper-with-me

Papers

Hierarchical Decision Making by Generating and Following Natural Language Instructions

2019-06-03 · NeurIPS 2019 12 · Hengyuan Hu, Denis Yarats, Qucheng Gong, Yuandong Tian, Mike Lewis

We explore using latent natural language instructions as an expressive and compositional representation of complex actions for hierarchical decision making. Rather than directly selecting micro-actions, our agent first generates a latent plan in natural language, which is then executed by a separate model. We introduce a challenging real-time strategy game environment in which the actions of a large number of units must be coordinated across long time scales. We gather a dataset of 76 thousand pairs of instructions and executions from human play, and train instructor and executor models. Experiments show that models using natural language as a latent variable significantly outperform models that directly imitate human actions. The compositional structure of language proves crucial to its effectiveness for action representation. We also release our code, models and data.

📄 PDF Abstract BibTeX arXiv:1906.00744

Code (1)

facebookresearch/minirts 공식 구현 pytorch

Tasks

Decision Making

Similar Papers 제목 키워드 기반

Skill Induction and Planning with Latent Language

2021-11-16 · ACL ARR November 2021 11 · Anonymous

We present a framework for learning hierarchical policies from demonstrations, using sparse natural language annotations to guide the discovery of reusable skills for autonomous decision-making. We formulate a generative…

Decision MakingInstruction Following

NILE : Natural Language Inference with Faithful Natural Language Explanations

2020-05-25 · ACL 2020 6 · Sawan Kumar, Partha Talukdar

The recent growth in the popularity and success of deep learning models on NLP classification tasks has accompanied the need for generating some form of natural language explanation of the predicted labels. Such generate…

Decision MakingNatural Language InferenceSensitivity

A Survey of Reinforcement Learning Informed by Natural Language

2019-06-10 · Jelena Luketina, Nantas Nardelli, Gregory Farquhar, Jakob Foerster 외

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 …

Decision MakingInstruction FollowingNatural Language Understandingreinforcement-learning+5

Single photon in hierarchical architecture for physical reinforcement learning: Photon intelligence

2016-09-01 · Makoto Naruse, Martin Berthel, Aurélien Drezet, Serge Huant 외

Understanding and using natural processes for intelligent functionalities, referred to as natural intelligence, has recently attracted interest from a variety of fields, including post-silicon computing for artificial in…

Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Generating Hierarchical Explanations on Text Classification via Feature Interaction Detection

2020-04-04 · ACL 2020 6 · Hanjie Chen, Guangtao Zheng, Yangfeng Ji

Generating explanations for neural networks has become crucial for their applications in real-world with respect to reliability and trustworthiness. In natural language processing, existing methods usually provide import…

ClassificationDecision MakingGeneral Classificationtext-classification+1