Related papers: Neural MMO: A Massively Multiagent Game Environmen…
Building autonomous -- i.e., choosing goals based on one's needs -- and adaptive -- i.e., surviving in ever-changing environments -- agents has been a holy grail of artificial intelligence (AI). A living organism is a prime example of such…
MOBA games, e.g., Honor of Kings, League of Legends, and Dota 2, pose grand challenges to AI systems such as multi-agent, enormous state-action space, complex action control, etc. Developing AI for playing MOBA games has raised much…
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…
The diversity of agent behaviors is an important topic for the quality of video games and virtual environments in general. Offering the most compelling experience for users with different skills is a difficult task, and usually needs…
When creating policies, plans, or designs for people, it is challenging for designers to foresee all of the ways in which people may reason and behave. Recently, Large Language Models (LLMs) have been shown to be able to simulate human…
We construct a model of social behaviour through the dynamics of interacting agents. The agents undergo game-theoretic interactions where each agent can decide to lend support to particular other agents or otherwise, and agents are rewarded…
Research concerning organization and coordination within multi-agent systems continues to draw from a variety of architectures and methodologies. The work presented in this paper combines techniques from game theory and multi-agent systems…
Large language model (LLM) agents are increasingly deployed in competitive multi-agent settings, raising fundamental questions about whether they converge to equilibria and how their strategic behavior can be characterized. In this paper,…
Learning how to adapt to complex and dynamic environments is one of the most important factors that contribute to our intelligence. Endowing artificial agents with this ability is not a simple task, particularly in competitive scenarios. In…
Many real-world scenarios involve teams of agents that have to coordinate their actions to reach a shared goal. We focus on the setting in which a team of agents faces an opponent in a zero-sum, imperfect-information game. Team members can…
Many potential applications of reinforcement learning in the real world involve interacting with other agents whose numbers vary over time. We propose new neural policy architectures for these multi-agent problems. In contrast to other…
A central problem in the theory of multi-agent reinforcement learning (MARL) is to understand what structural conditions and algorithmic principles lead to sample-efficient learning guarantees, and how these considerations change as we move…
We derive a class of macroscopic differential equations that describe collective adaptation, starting from a discrete-time stochastic microscopic model. The behavior of each agent is a dynamic balance between adaptation that locally…
A common vision from science fiction is that robots will one day inhabit our physical spaces, sense the world as we do, assist our physical labours, and communicate with us through natural language. Here we study how to design artificial…
The behavioral dynamics of multi-agent systems have a rich and orderly structure, which can be leveraged to understand these systems, and to improve how artificial agents learn to operate in them. Here we introduce Relational Forward Models…
Balancing game difficulty in video games is a key task to create interesting gaming experiences for players. Mismatching the game difficulty and a player's skill or commitment results in frustration or boredom on the player's side, and…
This chapter outlines the relation between artificial intelligence (AI) / machine learning (ML) algorithms and digital games. This relation is two-fold: on one hand, AI/ML researchers can generate large, in-the-wild datasets of human…
Multi-turn, multi-agent LLM game evaluations often exhibit substantial run-to-run variance. In long-horizon interactions, small early deviations compound across turns and are amplified by multi-agent coupling. This biases win rate estimates…
We introduce MAgent, a platform to support research and development of many-agent reinforcement learning. Unlike previous research platforms on single or multi-agent reinforcement learning, MAgent focuses on supporting the tasks and the…
In the pursuit of artificial general intelligence, our most significant measurement of progress is an agent's ability to achieve goals in a wide range of environments. Existing platforms for constructing such environments are typically…