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

Source: [What Should I Do Now? Marrying Reinforcement Learning and Symbolic Planning](<https://www.sota2.com/research/paper/68fa65361e209131cea08fd0>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:21:52.901Z

Authors: Daniel Gordon, Dieter Fox, Ali Farhadi

Published: 2019-01-06T03:15:15.000Z

## Abstract

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

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1901.01492>)

[PDF](<https://arxiv.org/pdf/1901.01492.pdf>)
