Related papers: Learning to Ground Multi-Agent Communication with …
In the real world, linguistic agents are also embodied agents: they perceive and act in the physical world. The notion of Language Grounding questions the interactions between language and embodiment: how do learning agents connect or…
Consider a collaborative task carried out by two autonomous agents that are able to communicate over a noisy channel. Each agent is only aware of its own state, while the accomplishment of the task depends on the value of the joint state of…
Communication between embodied AI agents has received increasing attention in recent years. Despite its use, it is still unclear whether the learned communication is interpretable and grounded in perception. To study the grounding of…
This paper introduces a methodology through which a population of autonomous agents can establish a linguistic convention that enables them to refer to arbitrary entities that they observe in their environment. The linguistic convention…
We introduce a task and dataset for referring expression generation and comprehension in multi-agent embodied environments. In this task, two agents in a shared scene must take into account one another's visual perspective, which may be…
Communication between agents in collaborative multi-agent settings is in general implicit or a direct data stream. This paper considers text-based natural language as a novel form of communication between multiple agents trained with…
Recent work on learning multilingual word representations usually relies on the use of word-level alignements (e.g. infered with the help of GIZA++) between translated sentences, in order to align the word embeddings in different languages.…
Effective communication is required for teams of robots to solve sophisticated collaborative tasks. In practice it is typical for both the encoding and semantics of communication to be manually defined by an expert; this is true regardless…
To cooperate with humans effectively, virtual agents need to be able to understand and execute language instructions. A typical setup to achieve this is with a scripted teacher which guides a virtual agent using language instructions.…
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…
Emergent communication offers insight into how agents develop shared structured representations, yet most research assumes homogeneous modalities or aligned representational spaces, overlooking the perceptual heterogeneity of real-world…
Grounding is the collaborative process of establishing mutual belief sufficient for a communicative goal. While static grounding maps language to a shared context, dynamic grounding requires agents to negotiate meaning across turns. Current…
Training agents to communicate with one another given task-based supervision only has attracted considerable attention recently, due to the growing interest in developing models for human-agent interaction. Prior work on the topic focused…
We present a method for combining multi-agent communication and traditional data-driven approaches to natural language learning, with an end goal of teaching agents to communicate with humans in natural language. Our starting point is a…
Situated dialogue requires speakers to maintain a reliable representation of shared context rather than reasoning only over isolated utterances. Current conversational agents often struggle with this requirement, especially when the common…
In this work, we propose a novel memory-based multi-agent meta-learning architecture and learning procedure that allows for learning of a shared communication policy that enables the emergence of rapid adaptation to new and unseen…
The problem of achieving common understanding between agents that use different vocabularies has been mainly addressed by designing techniques that explicitly negotiate mappings between their vocabularies, requiring agents to share a…
Common ground plays a critical role in situated spoken dialogs, where interlocutors must establish and maintain shared references to entities, events, and relations to sustain coherent interaction in a shared space and over time. With the…
Communicating in natural language is a powerful tool in multi-agent settings, as it enables independent agents to share information in partially observable settings and allows zero-shot coordination with humans. However, most prior works…
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 human language…