相关论文: Learning Emergent Discrete Message Communication f…

Recently, there has been increasing interest in transparency and interpretability in Deep Reinforcement Learning (DRL) systems. Verbal explanations, as the most natural way of communication in our daily life, deserve more attention, since…

Multiagent reinforcement learning (MARL) has attracted considerable attention due to its potential in addressing complex cooperative tasks. However, existing MARL approaches often rely on frequent exchanges of action or state information…

Recent progress on large language models (LLMs) has enabled dialogue agents to generate highly naturalistic and plausible text. However, current LLM language generation focuses on responding accurately to questions and requests with a…

The complexity of multiagent reinforcement learning (MARL) in multiagent systems increases exponentially with respect to the agent number. This scalability issue prevents MARL from being applied in large-scale multiagent systems. However,…

We propose a targeted communication architecture for multi-agent reinforcement learning, where agents learn both what messages to send and whom to address them to while performing cooperative tasks in partially-observable environments. This…

Communication has been widely employed to enhance multi-agent collaboration. Previous research has typically assumed delay-free communication, a strong assumption that is challenging to meet in practice. However, real-world agents suffer…

Multi-agent systems built on large language models have shown strong performance on complex reasoning tasks, yet most work focuses on agent roles and orchestration while treating inter-agent communication as a fixed interface. Latent…

Variational autoencoders have been widely applied for natural language generation, however, there are two long-standing problems: information under-representation and posterior collapse. The former arises from the fact that only the last…

Reinforcement learning (RL) has shown great promise for developing dialogue management (DM) agents that are non-myopic, conduct rich conversations, and maximize overall user satisfaction. Despite recent developments in RL and language…

Decentralized Multi-Agent Reinforcement Learning (MARL) methods allow for learning scalable multi-agent policies, but suffer from partial observability and induced non-stationarity. These challenges can be addressed by introducing…

Several recent works have found the emergence of grounded compositional language in the communication protocols developed by mostly cooperative multi-agent systems when learned end-to-end to maximize performance on a downstream task.…

In this work, we propose a computational framework in which agents equipped with communication capabilities simultaneously play a series of referential games, where agents are trained using deep reinforcement learning. We demonstrate that…

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…

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…

Cooperative intelligence (CI) is expected to become an integral element in next-generation networks because it can aggregate the capabilities and intelligence of multiple devices. Multi-agent reinforcement learning (MARL) is a popular…

Discrete and continuous representations of content (e.g., of language or images) have interesting properties to be explored for the understanding of or reasoning with this content by machines. This position paper puts forward our opinion on…

We present a reinforcement learning strategy for use in multi-agent foraging systems in which the learning is centralised to a single agent and its model is periodically disseminated among the population of non-learning agents. In a domain…

In the recent shift towards human-centric AI, the need for machines to accurately use natural language has become increasingly important. While a common approach to achieve this is to train large language models, this method presents a form…

Large Language Models (LLMs) have revolutionized Natural Language Processing but exhibit limitations, particularly in autonomously addressing novel challenges such as reasoning and problem-solving. Traditional techniques like…

In Decentralized Multi-Agent Reinforcement Learning (MARL), the development of Emergent Communication has long been constrained by the ``Joint Exploration Dilemma'', leading agents to fall into a ``Communication Vacuum Equilibrium'' .…