Zero-Shot Generalization using Intrinsically Motivated Compositional Emergent Protocols
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'?}.
Code (1)
Tasks
Zero-shot GeneralizationSimilar Papers 제목 키워드 기반
Curiosity-Driven Development of Action and Language in Robots Through Self-Exploration
Infants acquire language with generalization from minimal experience, whereas large language models require billions of training tokens. What underlies efficient development in humans? We investigated this problem throug…
Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation
It has been a long-standing dream to design artificial agents that explore their environment efficiently via intrinsic motivation, similar to how children perform curious free play. Despite recent advances in intrinsical…
Efficient ExplorationObjectReinforcement Learning (RL)Zero-shot GeneralizationSEQZERO: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Models
Recent research showed promising results on combining pretrained language models (LMs) with canonical utterance for few-shot semantic parsing.The canonical utterance is often lengthy and complex due to the compositional …
Out-of-Distribution GeneralizationSemantic ParsingZero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning
Humans are capable of abstracting various tasks as different combinations of multiple attributes. This perspective of compositionality is vital for human rapid learning and adaption since previous experiences from relate…
DisentanglementMeta Reinforcement Learningreinforcement-learningReinforcement Learning (RL)SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Models
Recent research showed promising results on combining pretrained language models (LMs) with canonical utterance for few-shot semantic parsing. The canonical utterance is often lengthy and complex due to the compositional…
Out-of-Distribution GeneralizationSemantic Parsing