Few-shot Subgoal Planning with Language Models
release_dn46md4hg5hqnogal5cmsrahru
by
Lajanugen Logeswaran, Yao Fu, Moontae Lee, Honglak Lee
2022
Abstract
Pre-trained large language models have shown successful progress in many
language understanding benchmarks. This work explores the capability of these
models to predict actionable plans in real-world environments. Given a text
instruction, we show that language priors encoded in pre-trained language
models allow us to infer fine-grained subgoal sequences. In contrast to recent
methods which make strong assumptions about subgoal supervision, our
experiments show that language models can infer detailed subgoal sequences from
few training sequences without any fine-tuning. We further propose a simple
strategy to re-rank language model predictions based on interaction and
feedback from the environment. Combined with pre-trained navigation and visual
reasoning components, our approach demonstrates competitive performance on
subgoal prediction and task completion in the ALFRED benchmark compared to
prior methods that assume more subgoal supervision.
In text/plain
format
Archived Files and Locations
application/pdf 1.2 MB
file_lfmo4bsu4zambdh26fns2733uy
|
arxiv.org (repository) web.archive.org (webarchive) |
2205.14288v1
access all versions, variants, and formats of this works (eg, pre-prints)