What Should I Do Now? Marrying Reinforcement Learning and Symbolic Planning

By Daniel Gordon, Dieter Fox, Ali Farhadi. 2019

21 citations recorded by the source corpus.

Long-term planning poses a major difficulty to many reinforcement learning algorithms. This problem becomes even more pronounced in dynamic visual environments. In this work we propose Hierarchical Planning and Reinforcement Learning (HIP-RL), a method for merging the benefits and capabilities of Symbolic Planning with the learning abilities of Deep Reinforcement Learning. We apply HIPRL to the complex visual tasks of interactive question answering and visual semantic planning and achieve state-of-the-art results on three challenging datasets all while taking fewer steps at test time and training in fewer iterations. Sample results can be found at youtu.be/0TtWJ_0mPfI

Subfields: Artificial Intelligence, Natural Language Processing, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

In Reinforcement Learning

Citations in the corpus

ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks (2019, background): “Previous work in the original AI2-THOR environment investigated the task of visual semantic planning [19, 57].”
From Seeing to Moving: A Survey on Learning for Visual Indoor Navigation (VIN) (2020, background): “More advanced variations can be found in [Das et al., 2018b; Gordon et al., 2019; Yu et al., 2019; Wijmans et al., 2019].”