Related papers: Inductive Bias for Emergent Communication in a Con…

Multi-Agent Reinforcement Learning (MARL) methods find optimal policies for agents that operate in the presence of other learning agents. Central to achieving this is how the agents coordinate. One way to coordinate is by learning to…

By the age of two, children tend to assume that new word categories are based on objects' shape, rather than their color or texture; this assumption is called the shape bias. They are thought to learn this bias by observing that their…

Mobile augmented reality (MAR) is widely acknowledged as one of the ubiquitous interfaces to the digital twin and Metaverse, demanding unparalleled levels of latency, computational power, and energy efficiency. The existing solutions for…

A hallmark of life on Earth is the ability of agents to exert causal power and be drivers of subsequent events. This is key to cognition at all scales. Causal emergence, measuring the degree to which an agent exerts unique predictive power…

Recently, emergence of signaling conventions, among which language is a prime example, draws a considerable interdisciplinary interest ranging from game theory, to robotics to evolutionary linguistics. Such a wide spectrum of research is…

Animals learn to predict external contingencies from experience through a process of conditioning. A natural mechanism for conditioning is stimulus substitution, whereby the neuronal response to a stimulus with no prior behavioral…

Interactive reinforcement learning agents use human feedback or instruction to help them learn in complex environments. Often, this feedback comes in the form of a discrete signal that is either positive or negative. While informative, this…

Recent research studies communication emergence in communities of deep network agents assigned a joint task, hoping to gain insights on human language evolution. We propose here a new task capturing crucial aspects of the human environment,…

Communication is not only an action of choosing a signal, but needs to consider the context and sensor signals. It also needs to decide what information is communicated and how it is represented in or understood from signals. Therefore,…

Communication lays the foundation for human cooperation. It is also crucial for multi-agent cooperation. However, existing work focuses on broadcast communication, which is not only impractical but also leads to information redundancy that…

Individuals, despite having varied life experiences and learning processes, can communicate effectively through languages. This study aims to explore the efficiency of language as a communication medium. We put forth two specific…

This paper is concerned with the training of recurrent neural networks as goal-oriented dialog agents using reinforcement learning. Training such agents with policy gradients typically requires a large amount of samples. However, the…

Emergence is a fascinating property of large language models and neural networks more broadly: as models scale and train for longer, they sometimes develop new abilities in sudden ways. Despite initial studies, we still lack a comprehensive…

The ability to pick up on language signals in an ongoing interaction is crucial for future machine learning models to collaborate and interact with humans naturally. In this paper, we present an initial study that evaluates intra-episodic…

Natural languages display a trade-off among different strategies to convey syntactic structure, such as word order or inflection. This trade-off, however, has not appeared in recent simulations of iterated language learning with neural…

While end-to-end neural conversation models have led to promising advances in reducing hand-crafted features and errors induced by the traditional complex system architecture, they typically require an enormous amount of data due to the…

We examine the problem of learning to cooperate in the context of wireless communication. In our setting, two agents must learn modulation schemes that enable them to communicate across a power-constrained additive white Gaussian noise…

While current deep learning systems excel at tasks such as object classification, language processing, and gameplay, few can construct or modify a complex system such as a tower of blocks. We hypothesize that what these systems lack is a…

Multi-agent reinforcement learning (MARL) extends (single-agent) reinforcement learning (RL) by introducing additional agents and (potentially) partial observability of the environment. Consequently, algorithms for solving MARL problems…

We study systems of interacting reinforced stochastic processes, where agents' decisions evolve under reinforcement, network-mediated interactions, and environmental influences. In competitive environments with irreducible networks, we…