Compositional Understanding in Signaling Games
Receivers in standard signaling game models struggle with learning compositional information. Even when the signalers send compositional messages, the receivers do not interpret them compositionally. When information from one message component is lost or forgotten, the information from other components is also erased. In this paper I construct signaling game models in which genuine compositional understanding evolves. I present two new models: a minimalist receiver who only learns from the atomic messages of a signal, and a generalist receiver who learns from all of the available information. These models are in many ways simpler than previous alternatives, and allow the receivers to learn from the atomic components of messages.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Emergent Communication: Generalization and Overfitting in Lewis Games
Lewis signaling games are a class of simple communication games for simulating the emergence of language. In these games, two agents must agree on a communication protocol in order to solve a cooperative task. Previous w…
On the Spontaneous Emergence of Discrete and Compositional Signals
We propose a general framework to study language emergence through signaling games with neural agents. Using a continuous latent space, we are able to (i) train using backpropagation, (ii) show that discrete messages non…
Emergence of compositional language in communication through noisy channel
In this paper, we investigate how communication through a noisy channel can lead to the emergence of compositional language. Our approach is $\mbox{end-to-end}$, allows for different inductive biases on the agents’ archi…
Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication
Communication is compositional if complex signals can be represented as a combination of simpler subparts. In this paper, we theoretically show that inductive biases on both the training framework and the data are needed…
Algorithmic Information Design in Multi-Player Games: Possibility and Limits in Singleton Congestion
Most algorithmic studies on multi-agent information design so far have focused on the restricted situation with no inter-agent externalities; a few exceptions investigated truly strategic games such as zero-sum games and…
Scheduling