Co-evolution of language and agents in referential games
Referential games offer a grounded learning environment for neural agents which accounts for the fact that language is functionally used to communicate. However, they do not take into account a second constraint considered to be fundamental for the shape of human language: that it must be learnable by new language learners. Cogswell et al. (2019) introduced cultural transmission within referential games through a changing population of agents to constrain the emerging language to be learnable. However, the resulting languages remain inherently biased by the agents' underlying capabilities. In this work, we introduce Language Transmission Engine to model both cultural and architectural evolution in a population of agents. As our core contribution, we empirically show that the optimal situation is to take into account also the learning biases of the language learners and thus let language and agents co-evolve. When we allow the agent population to evolve through architectural evolution, we achieve across the board improvements on all considered metrics and surpass the gains made with cultural transmission. These results stress the importance of studying the underlying agent architecture and pave the way to investigate the co-evolution of language and agent in language emergence studies.
Code (1)
Similar Papers 제목 키워드 기반
Co-evolution of language and agents in referential games
Referential games offer a grounded learning environment for neural agents which accounts for the fact that language is functionally used to communicate. However, they do not take into account a second constraint consider…
Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input
The ability of algorithms to evolve or learn (compositional) communication protocols has traditionally been studied in the language evolution literature through the use of emergent communication tasks. Here we scale up t…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Emergent Linguistic Phenomena in Multi-Agent Communication Games
In this work, we propose a computational framework in which agents equipped with communication capabilities simultaneously play a series of referential games, where agents are trained using deep reinforcement learning. W…
Deep Reinforcement LearningReinforcement LearningReinforcement Learning (RL)Meta-Referential Games to Learn Compositional Learning Behaviours
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…
Meta-LearningSystematic GeneralizationEmergence of Multilingualism in Population based Referential Games
The ability of agents to learn to communicate by interaction has been studied through emergent communication tasks. Inspired by previous work in this domain, we extend the referential game setup to a population of spatia…