Meta-Referential Games to Learn Compositional Learning Behaviours

Kevin Yandoka Denamganai, Sondess Missaoui, James Alfred Walker

Primary Area: datasets and benchmarks

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: referential game, language grounding, compositionality, systematicity, few-shot learning, meta-learning, reinforcement learning, language emergence

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We present a novel framework of Meta-Referential Games upon which we built a novel benchmark, the Symbolic Behaviour Benchmark, and use it in an initial study to evaluate AIs' abilities to learn compositional learning behaviours.

Abstract:

Human beings use compositionality to generalise from past experiences to novel experiences. We assume a separation of our experiences into fundamental atomic components that can be recombined in novel ways to support our ability to engage with novel experiences. We frame this as the ability to learn to generalise compositionally, and we will refer to behaviours making use of this ability as compositional learning behaviours (CLBs).

A central problem to learning CLBs is the resolution of a binding problem (BP). While it is another feat of intelligence that human beings perform with ease, it is not the case for state-of-the-art artificial agents. Thus, in order to build artificial agents able to collaborate with human beings, we propose to develop a novel benchmark to investigate agents’ abilities to exhibit CLBs by solving a domain-agnostic version of the BP.

We take inspiration from the language emergence and grounding framework of referential games and propose a meta-learning extension of referential games, entitled Meta-Referential Games, and use this framework to build our benchmark, that we name Symbolic Behaviour Benchmark (S2B). We provide baseline results and error analysis showing that our benchmark is a compelling challenge that we hope will spur the research community towards developing more capable artificial agents.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 5753