A Deep Compositional Framework for Human-like Language Acquisition in Virtual Environment
We tackle a task where an agent learns to navigate in a 2D maze-like environment called XWORLD. In each session, the agent perceives a sequence of raw-pixel frames, a natural language command issued by a teacher, and a set of rewards. The agent learns the teacher's language from scratch in a grounded and compositional manner, such that after training it is able to correctly execute zero-shot commands: 1) the combination of words in the command never appeared before, and/or 2) the command contains new object concepts that are learned from another task but never learned from navigation. Our deep framework for the agent is trained end to end: it learns simultaneously the visual representations of the environment, the syntax and semantics of the language, and the action module that outputs actions. The zero-shot learning capability of our framework results from its compositionality and modularity with parameter tying. We visualize the intermediate outputs of the framework, demonstrating that the agent truly understands how to solve the problem. We believe that our results provide some preliminary insights on how to train an agent with similar abilities in a 3D environment.
Code (0)
등록된 구현이 없습니다.
Tasks
Language AcquisitionNavigateZero-Shot LearningSimilar Papers 제목 키워드 기반
Visually Grounded Continual Learning of Compositional Phrases
Humans acquire language continually with much more limited access to data samples at a time, as compared to contemporary NLP systems. To study this human-like language acquisition ability, we present VisCOLL, a visually …
Continual LearningGrounded language learningLanguage AcquisitionLanguage ModellingTowards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channel
Multi-agent reinforcement learning has been used as an effective means to study emergent communication between agents, yet little focus has been given to continuous acoustic communication. This would be more akin to huma…
Language AcquisitionMulti-agent Reinforcement LearningQ-Learningreinforcement-learning+1On the Correspondence between Compositionality and Imitation in Emergent Neural Communication
Compositionality is a hallmark of human language that not only enables linguistic generalization, but also potentially facilitates acquisition. When simulating language emergence with neural networks, compositionality ha…
Imitation LearningEmergent Language Generalization and Acquisition Speed are not tied to Compositionality
Studies of discrete languages emerging when neural agents communicate to solve a joint task often look for evidence of compositional structure. This stems for the expectation that such a structure would allow languages t…
Are we Forgetting about Compositional Optimisers in Bayesian Optimisation?
Bayesian optimisation presents a sample-efficient methodology for global optimisation. Within this framework, a crucial performance-determining subroutine is the maximisation of the acquisition function, a task complicat…
Bayesian Optimisation