Keywords: language, learning, efficiency, imitation learning, reinforcement learning
TL;DR: We present the BabyAI platform for studying data efficiency of language learning with a human in the loop
Abstract: Allowing humans to interactively train artificial agents to understand language instructions is desirable for both practical and scientific reasons. Though, given the lack of sample efficiency in current learning methods, reaching this goal may require substantial research efforts. We introduce the BabyAI research platform, with the goal of supporting investigations towards including humans in the loop for grounded language learning. The BabyAI platform comprises an extensible suite of 19 levels of increasing difficulty. Each level gradually leads the agent towards acquiring a combinatorially rich synthetic language, which is a proper subset of English. The platform also provides a hand-crafted bot agent, which simulates a human teacher. We report estimated amount of supervision required for training neural reinforcement and behavioral-cloning agents on some BabyAI levels. We put forward strong evidence that current deep learning methods are not yet sufficiently sample-efficient in the context of learning a language with compositional properties.
Code: [![github](/images/github_icon.svg) mila-iqia/babyai](https://github.com/mila-iqia/babyai) + [![Papers with Code](/images/pwc_icon.svg) 5 community implementations](https://paperswithcode.com/paper/?openreview=rJeXCo0cYX)
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 4 code implementations](https://www.catalyzex.com/paper/arxiv:1810.08272/code)