Related papers: Learning to Ground Decentralized Multi-Agent Commu…
This paper introduces a decentralized multi-agent reinforcement learning framework enabling structurally heterogeneous teams of agents to jointly discover and acquire randomly located targets in environments characterized by partial…
The study of emergent communication has been dedicated to interactive artificial intelligence. While existing work focuses on communication about single objects or complex image scenes, we argue that communicating relationships between…
The literature in modern machine learning has only negative results for learning to communicate between competitive agents using standard RL. We introduce a modified sender-receiver game to study the spectrum of partially-competitive…
This paper introduces a novel transfer learning framework for deep multi-agent reinforcement learning. The approach automatically combines goal-conditioned policies with temporal contrastive learning to discover meaningful sub-goals. The…
Cooperative multi-agent reinforcement learning (MARL) has achieved significant results, most notably by leveraging the representation-learning abilities of deep neural networks. However, large centralized approaches quickly become…
In typical multi-agent reinforcement learning (MARL) problems, communication is important for agents to share information and make the right decisions. However, due to the complexity of training multi-agent communication, existing methods…
This paper addresses the limitations of a single agent in task decomposition and collaboration during complex task execution, and proposes a multi-agent architecture for modular task decomposition and dynamic collaboration based on large…
Multi-agent LLM systems improve reasoning by combining outputs from multiple agents, but interaction-heavy methods can introduce error propagation and high communication overhead. When agents exchange raw responses or reasoning traces,…
Human intelligence has the remarkable ability to quickly adapt to new tasks and environments. Starting from a very young age, humans acquire new skills and learn how to solve new tasks either by imitating the behavior of others or by…
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…
With the increasing prevalence and diversity of robots interacting in the real world, there is need for flexible, on-the-fly planning and cooperation. Large Language Models are starting to be explored in a multimodal setup for…
Humans generally use natural language to communicate task requirements to each other. Ideally, natural language should also be usable for communicating goals to autonomous machines (e.g., robots) to minimize friction in task specification.…
The rapid development of the Large Language Model (LLM) presents huge opportunities for 6G communications, e.g., network optimization and management by allowing users to input task requirements to LLMs by nature language. However, directly…
Traditional methods plan feasible paths for multiple agents in the stochastic environment. However, the methods' iterations with the changes in the environment result in computation complexities, especially for the decentralized agents…
Goal-oriented conversational agents are becoming prevalent in our daily lives. For these systems to engage users and achieve their goals, they need to exhibit appropriate social behavior as well as provide informative replies that guide…
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…
Eliciting cooperation in multi-agent LLM systems is critical for AI alignment. We investigate two approaches: direct communication and curriculum learning. In a 4-player Stag Hunt, a one-word "cheap talk" channel increases cooperation from…
Differential Case Marking (DCM) refers to the phenomenon where grammatical case marking is applied selectively based on semantic, pragmatic, or other factors. The emergence of DCM has been studied in artificial language learning experiments…
Building dialog agents that can converse naturally with humans is a challenging yet intriguing problem of artificial intelligence. In open-domain human-computer conversation, where the conversational agent is expected to respond to human…
Effective communication requires adapting to the idiosyncrasies of each communicative context--such as the common ground shared with each partner. Humans demonstrate this ability to specialize to their audience in many contexts, such as the…