Related papers: Ease-of-Teaching and Language Structure from Emerg…
Understanding the mechanisms behind emergent behaviors in multi-agent systems is critical for advancing fields such as swarm robotics and artificial intelligence. In this study, we investigate how neural networks evolve to control agents'…
We propose a framework that learns to execute natural language instructions in an environment consisting of goal-reaching tasks that share components of their task descriptions. Our approach leverages the compositionality of both value…
This paper discusses the problem of learning language from unprocessed text and speech signals, concentrating on the problem of learning a lexicon. In particular, it argues for a representation of language in which linguistic parameters…
In the last years there has been a growing interest in the study of learning problems associated with algebraic structures. The framework we use models the scenario in which a learner is given larger and larger fragments of a structure from…
Computational modelling with multi-agent systems is becoming an important technique of studying language evolution. We present a brief introduction into this rapidly developing field, as well as our own contributions that include an…
We study a neuro-inspired model that mimics a discussion (or information dissemination) process in a network of agents. During their interaction, agents redistribute activity and network weights, resulting in emergence of leader(s). The…
The fast changing reality in technical and natural domains perceived by always more accurate observations has drawn attention on new and very broad class of systems with specific behaviour represented under the common wording complexity.…
Compositionality is a cognitive mechanism that allows humans to systematically combine known concepts in novel ways. This study demonstrates how artificial neural agents acquire and utilize compositional generalization to describe…
As individuals communicate, their exchanges form a dynamic network. We demonstrate, using time series analysis of communication in three online settings, that network structure alone can be highly revealing of the diversity and novelty of…
A desirable property of an intelligent agent is its ability to understand its environment to quickly generalize to novel tasks and compose simpler tasks into more complex ones. If the environment has geometric or arithmetic structure, the…
This work explores the large-scale multi-agent communication mechanism under a multi-agent reinforcement learning (MARL) setting. We summarize the general categories of topology for communication structures in MARL literature, which are…
Composing basic skills from simple tasks to accomplish composite tasks is crucial for modern intelligent systems. We investigate the in-context composition ability of language models to perform composite tasks that combine basic skills…
Neural agents trained in reinforcement learning settings can learn to communicate among themselves via discrete tokens, accomplishing as a team what agents would be unable to do alone. However, the current standard of using one-hot vectors…
It is desirable for an agent to be able to solve a rich variety of problems that can be specified through language in the same environment. A popular approach towards obtaining such agents is to reuse skills learned in prior tasks to…
We consider the problem of designing an artificial agent capable of interacting with humans in collaborative dialogue to produce creative, engaging narratives. In this task, the goal is to establish universe details, and to collaborate on…
Transformer-based large language models are rapidly advancing in the field of machine learning research, with applications spanning natural language, biology, chemistry, and computer programming. Extreme scaling and reinforcement learning…
In most multiagent applications, communication is essential among agents to coordinate their actions, and thus achieve their goal. However, communication often has a related cost that affects overall system performance. In this paper, we…
To interact with humans and act in the world, agents need to understand the range of language that people use and relate it to the visual world. While current agents can learn to execute simple language instructions, we aim to build agents…
Self-supervised speech models learn effective representations of spoken language, which have been shown to reflect various aspects of linguistic structure. But when does such structure emerge in model training? We study the encoding of a…
Structured prediction is ubiquitous in applications of machine learning such as knowledge extraction and natural language processing. Structure often can be formulated in terms of logical constraints. We consider the question of how to…