Zero-Shot Generalization using Intrinsically Motivated Compositional Emergent Protocols
This addresses the challenge of improving AI generalization and adaptability, though it appears incremental by building on prior work in curiosity-driven language development.
The paper tackles the problem of enabling artificial agents to generalize to unseen tasks through compositional communication protocols, demonstrating that agents trained with intrinsic motivation can achieve zero-shot generalization, such as performing 'pull twice' after learning 'pull' and 'push twice'.
Human language has been described as a system that makes \textit{use of finite means to express an unlimited array of thoughts}. Of particular interest is the aspect of compositionality, whereby, the meaning of a compound language expression can be deduced from the meaning of its constituent parts. If artificial agents can develop compositional communication protocols akin to human language, they can be made to seamlessly generalize to unseen combinations. Studies have recognized the role of curiosity in enabling linguistic development in children. In this paper, we seek to use this intrinsic feedback in inducing a systematic and unambiguous protolanguage. We demonstrate how compositionality can enable agents to not only interact with unseen objects but also transfer skills from one task to another in a zero-shot setting: \textit{Can an agent, trained to `pull' and `push twice', `pull twice'?}.