Related papers: Cross-environment Cooperation Enables Zero-shot Mu…

Over these years, multi-agent reinforcement learning has achieved remarkable performance in multi-agent planning and scheduling tasks. It typically follows the self-play setting, where agents are trained by playing with a fixed group of…

Zero-shot classification (ZSC) is the task of learning predictors for classes not seen during training. Although the different methods in the literature are evaluated using the same class splits, little is known about their stability under…

Zero-shot coordination in cooperative artificial intelligence (AI) remains a significant challenge, which means effectively coordinating with a wide range of unseen partners. Previous algorithms have attempted to address this challenge by…

Learning accurate models of the physical world is required for a lot of robotic manipulation tasks. However, during manipulation, robots are expected to interact with unknown workpieces so that building predictive models which can…

In collaborative tasks, autonomous agents fall short of humans in their capability to quickly adapt to new and unfamiliar teammates. We posit that a limiting factor for zero-shot coordination is the lack of shared task abstractions, a…

Effective coordination is crucial to solve multi-agent collaborative (MAC) problems. While centralized reinforcement learning methods can optimally solve small MAC instances, they do not scale to large problems and they fail to generalize…

A significant element of human cooperative intelligence lies in our ability to identify opportunities for fruitful collaboration; and conversely to recognise when the task at hand is better pursued alone. Research on flexible cooperation in…

While multi-agent interactions can be naturally modeled as a graph, the environment has traditionally been considered as a black box. We propose to create a shared agent-entity graph, where agents and environmental entities form vertices,…

Real-world multi-agent systems may require ad hoc teaming, where an agent must coordinate with other previously unseen teammates to solve a task in a zero-shot manner. Prior work often either selects a pretrained policy based on an inferred…

Building a single generalist agent with strong zero-shot capability has recently sparked significant advancements. However, extending this capability to multi-agent decision making scenarios presents challenges. Most current works struggle…

The paradigm of agentic AI is shifting from engineered complex workflows to post-training native models. However, existing agents are typically confined to static, predefined action spaces--such as exclusively using APIs, GUI events, or…

Training agents that can coordinate zero-shot with humans is a key mission in multi-agent reinforcement learning (MARL). Current algorithms focus on training simulated human partner policies which are then used to train a Cooperator agent.…

Humans perceive the world through multiple senses, enabling them to create a comprehensive representation of their surroundings and to generalize information across domains. For instance, when a textual description of a scene is given,…

A central challenge in multi-agent reinforcement learning is enabling agents to adapt to previously unseen teammates in a zero-shot fashion. Prior work in zero-shot coordination often follows a two-stage process, first generating a diverse…

In order to collaborate efficiently with unknown partners in cooperative control settings, adaptation of the partners based on online experience is required. The rather general and widely applicable control setting, where each cooperation…

Exploration in multi-agent reinforcement learning is a challenging problem, especially in environments with sparse rewards. We propose a general method for efficient exploration by sharing experience amongst agents. Our proposed algorithm,…

This paper introduces Team-Attention-Actor-Critic (TAAC), a reinforcement learning algorithm designed to enhance multi-agent collaboration in cooperative environments. TAAC employs a Centralized Training/Centralized Execution scheme…

We study the emergence of cooperative behaviors in reinforcement learning agents by introducing a challenging competitive multi-agent soccer environment with continuous simulated physics. We demonstrate that decentralized, population-based…

In many real-world problems, a team of agents need to collaborate to maximize the common reward. Although existing works formulate this problem into a centralized learning with decentralized execution framework, which avoids the…

In open multi-agent environments, the agents may encounter unexpected teammates. Classical multi-agent learning approaches train agents that can only coordinate with seen teammates. Recent studies attempted to generate diverse teammates to…