Related papers: Efficient Reinforcement Learning for Zero-Shot Coo…
Cooperative Multi-agent Reinforcement Learning (MARL) algorithms with Zero-Shot Coordination (ZSC) have gained significant attention in recent years. ZSC refers to the ability of agents to coordinate zero-shot (without additional…
Many Multi-Agent Reinforcement Learning (MARL) agents fail to adapt properly to cooperating with agents trained with the same objectives but different seeds, algorithms, or other training differences. This is the problem of Zero-Shot…
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 coordination (ZSC), the ability to adapt to a new partner in a cooperative task, is a critical component of human-compatible AI. While prior work has focused on training agents to cooperate on a single task, these specialized…
We study the problem of training a Reinforcement Learning (RL) agent that is collaborative with humans without using any human data. Although such agents can be obtained through self-play training, they can suffer significantly from…
Generating agents that can achieve zero-shot coordination (ZSC) with unseen partners is a new challenge in cooperative multi-agent reinforcement learning (MARL). Recently, some studies have made progress in ZSC by exposing the agents to…
Zero-shot coordination (ZSC) -- the ability to collaborate with unfamiliar partners -- is essential to making autonomous agents effective teammates. Existing ZSC methods evaluate coordination capabilities between two agents who have not…
The standard problem setting in cooperative multi-agent settings is self-play (SP), where the goal is to train a team of agents that works well together. However, optimal SP policies commonly contain arbitrary conventions ("handshakes") and…
Zero-shot coordination (ZSC) is a new cooperative multi-agent reinforcement learning (MARL) challenge that aims to train an ego agent to work with diverse, unseen partners during deployment. The significant difference between the…
Zero-shot coordination (ZSC) remains a major challenge in the cooperative AI field, which aims to learn an agent to cooperate with an unseen partner in training environments or even novel environments. In recent years, a popular ZSC…
Modern reinforcement learning (RL) systems capture deep truths about general, human problem-solving. In domains where new data can be simulated cheaply, these systems uncover sequential decision-making policies that far exceed the ability…
Zero-shot coordination (ZSC) aims to enable agents to cooperate with independently trained partners without prior interaction, a key requirement for real-world multi-agent systems and human-AI collaboration. Existing approaches have largely…
Zero-shot coordination problem in multi-agent reinforcement learning (MARL), which requires agents to adapt to unseen agents, has attracted increasing attention. Traditional approaches often rely on the Self-Play (SP) framework to generate…
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…
A major bottleneck in the training process for Zero-Shot Coordination (ZSC) agents is the generation of partner agents that are diverse in collaborative conventions. Current Cross-play Minimization (XPM) methods for population generation…
Current deep reinforcement learning (RL) algorithms are still highly task-specific and lack the ability to generalize to new environments. Lifelong learning (LLL), however, aims at solving multiple tasks sequentially by efficiently…
We consider the problem of zero-shot coordination - constructing AI agents that can coordinate with novel partners they have not seen before (e.g. humans). Standard Multi-Agent Reinforcement Learning (MARL) methods typically focus on the…
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.…
Zero-shot coordination (ZSC) is a popular setting for studying the ability of reinforcement learning (RL) agents to coordinate with novel partners. Prior ZSC formulations assume the $\textit{problem setting}$ is common knowledge: each agent…
Deep Reinforcement Learning (RL) models often fail to generalize when even small changes occur in the environment's observations or task requirements. Addressing these shifts typically requires costly retraining, limiting the reusability of…