Related papers: Biases for Emergent Communication in Multi-agent R…

Both entropy-minimizing and entropy-maximizing (curiosity) objectives for unsupervised reinforcement learning (RL) have been shown to be effective in different environments, depending on the environment's level of natural entropy. However,…

Popular methods in cooperative Multi-Agent Reinforcement Learning with partially observable environments typically allow agents to act independently during execution, which may limit the coordinated effect of the trained policies. However,…

Evidence that visual communication preceded written language and provided a basis for it goes back to prehistory, in forms such as cave and rock paintings depicting traces of our distant ancestors. Emergent communication research has sought…

Inferring the abstract relational and causal structure of the world is a major challenge for reinforcement-learning (RL) agents. For humans, language--particularly in the form of explanations--plays a considerable role in overcoming this…

Humans quite frequently interact with conversational agents. The rapid advancement in generative language modeling through neural networks has helped advance the creation of intelligent conversational agents. Researchers typically evaluate…

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…

We consider the problem of learning to communicate using multi-agent reinforcement learning (MARL). A common approach is to learn off-policy, using data sampled from a replay buffer. However, messages received in the past may not accurately…

Multi-agent sequential decision-making powers many real-world systems, from autonomous vehicles and robotics to collaborative AI assistants. In dynamic, partially observable environments, communication is often what reduces uncertainty and…

While speech-enabled teachable agents have some advantages over typing-based ones, they are vulnerable to errors stemming from misrecognition by automatic speech recognition (ASR). These errors may propagate, resulting in unexpected changes…

This paper surveys the field of deep multiagent reinforcement learning. The combination of deep neural networks with reinforcement learning has gained increased traction in recent years and is slowly shifting the focus from single-agent to…

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…

Contact between languages has the potential to transmit vocabulary and other language features; however, this does not always happen. Here, an iterated learning model is used to examine, in a simple way, the resistance of languages to…

When communicating, people behave consistently across conversational roles: People understand the words they say and are able to produce the words they hear. To date, artificial agents developed for language tasks have lacked such symmetry,…

How do learners acquire languages from the limited data available to them? This process must involve some inductive biases - factors that affect how a learner generalizes - but it is unclear which inductive biases can explain observed…

Recent findings in neuroscience suggest that the human brain represents information in a geometric structure (for instance, through conceptual spaces). In order to communicate, we flatten the complex representation of entities and their…

Large language models excel as few-shot learners when provided with appropriate demonstrations, yet this strength becomes problematic in multiturn agent scenarios, where LLMs erroneously mimic their own previous responses as few-shot…

The enactive approach to cognition is typically proposed as a viable alternative to traditional cognitive science. Enactive cognition displaces the explanatory focus from the internal representations of the agent to the direct sensorimotor…

We propose a method for training language models in an interactive setting inspired by child language acquisition. In our setting, a speaker attempts to communicate some information to a listener in a single-turn dialogue and receives a…

When developing reinforcement learning agents, the standard approach is to train an agent to converge to a fixed policy that is as close to optimal as possible for a single fixed reward function. If different agent behaviour is required in…

Inspired by previous work on emergent communication in referential games, we propose a novel multi-modal, multi-step referential game, where the sender and receiver have access to distinct modalities of an object, and their information…