English
Related papers

Related papers: Equivariant Networks for Zero-Shot Coordination

200 papers

Decentralized partially observable Markov decision processes (Dec-POMDPs) formalize the problem of designing individual controllers for a group of collaborative agents under stochastic dynamics and partial observability. Seeking a global…

Artificial Intelligence · Computer Science 2023-05-22 Yang You , Vincent Thomas , Francis Colas , Olivier Buffet

The inability to communicate poses a major challenge to coordination in multi-agent reinforcement learning (MARL). Prior work has explored correlating local policies via shared randomness, sometimes in the form of a correlation device, as a…

Multiagent Systems · Computer Science 2026-02-12 John Gardiner , Orlando Romero , Brendan Tivnan , Nicolò Dal Fabbro , George J. Pappas

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…

Multiagent Systems · Computer Science 2026-04-01 Rupal Nigam , Niket Parikh , Hamid Osooli , Mikihisa Yuasa , Jacob Heglund , Huy T. Tran

Zero-shot human-AI coordination holds the promise of collaborating with humans without human data. Prevailing methods try to train the ego agent with a population of partners via self-play. However, these methods suffer from two problems:…

Artificial Intelligence · Computer Science 2023-05-23 Xingzhou Lou , Jiaxian Guo , Junge Zhang , Jun Wang , Kaiqi Huang , Yali Du

Full parameter sharing is standard in cooperative multi-agent reinforcement learning (MARL) for homogeneous agents. Under permutation-symmetric observations, however, a shared deterministic policy outputs identical action distributions for…

Artificial Intelligence · Computer Science 2026-05-11 Rohan Patil , Jai Malegaonkar , Henrik I. Christensen

Recent superhuman results in games have largely been achieved in a variety of zero-sum settings, such as Go and Poker, in which agents need to compete against others. However, just like humans, real-world AI systems have to coordinate and…

Artificial Intelligence · Computer Science 2019-12-06 Adam Lerer , Hengyuan Hu , Jakob Foerster , Noam Brown

Group symmetries provide a powerful inductive bias for reinforcement learning (RL), enabling efficient generalization across symmetric states and actions via group-invariant Markov Decision Processes (MDPs). However, real-world environments…

Machine Learning · Computer Science 2026-03-12 Junwoo Chang , Minwoo Park , Joohwan Seo , Roberto Horowitz , Jongmin Lee , Jongeun Choi

Decentralized partially observable Markov decision processes (Dec-POMDPs) are rich models for cooperative decision-making under uncertainty, but are often intractable to solve optimally (NEXP-complete). The transition and observation…

Artificial Intelligence · Computer Science 2012-10-19 Jilles S. Dibangoye , Christopher Amato , Arnoud Doniec

Recent advances in hierarchical policy learning highlight the advantages of decomposing systems into high-level and low-level agents, enabling efficient long-horizon reasoning and precise fine-grained control. However, the interface between…

Robotics · Computer Science 2025-02-24 Haibo Zhao , Dian Wang , Yizhe Zhu , Xupeng Zhu , Owen Howell , Linfeng Zhao , Yaoyao Qian , Robin Walters , Robert Platt

Decentralized partially observable Markov decision processes with communication (Dec-POMDP-Com) provide a framework for multiagent decision making under uncertainty, but the NEXP-complete complexity for finite-horizon problems renders…

Multiagent Systems · Computer Science 2025-11-18 Dylan M. Asmar , Mykel J. Kochenderfer

Reinforcement learning (RL) in partially observable, fully cooperative multi-agent settings (Dec-POMDPs) can in principle be used to address many real-world challenges such as controlling a swarm of rescue robots or a team of quadcopters.…

Artificial Intelligence · Computer Science 2022-02-08 Qizhen Zhang , Chris Lu , Animesh Garg , Jakob Foerster

The standard problem setting in Dec-POMDPs is self-play, where the goal is to find a set of policies that play optimally together. Policies learned through self-play may adopt arbitrary conventions and implicitly rely on multi-step…

Artificial Intelligence · Computer Science 2021-08-19 Hengyuan Hu , Adam Lerer , Brandon Cui , David Wu , Luis Pineda , Noam Brown , Jakob Foerster

Effective communication is an important skill for enabling information exchange in multi-agent settings and emergent communication is now a vibrant field of research, with common settings involving discrete cheap-talk channels. Since, by…

Multiagent Systems · Computer Science 2021-06-23 Kalesha Bullard , Douwe Kiela , Franziska Meier , Joelle Pineau , Jakob Foerster

Autonomous agents are limited in their ability to observe the world state. Partially observable Markov decision processes (POMDPs) formally model the problem of planning under world state uncertainty, but POMDPs with continuous actions and…

Robotics · Computer Science 2020-07-08 Dicong Qiu , Yibiao Zhao , Chris L. Baker

This paper introduces MDP homomorphic networks for deep reinforcement learning. MDP homomorphic networks are neural networks that are equivariant under symmetries in the joint state-action space of an MDP. Current approaches to deep…

Machine Learning · Computer Science 2021-01-21 Elise van der Pol , Daniel E. Worrall , Herke van Hoof , Frans A. Oliehoek , Max Welling

Adversarial examples reveal critical vulnerabilities in deep neural networks by exploiting their sensitivity to imperceptible input perturbations. While adversarial training remains the predominant defense strategy, it often incurs…

Machine Learning · Computer Science 2025-11-04 Longwei Wang , Ifrat Ikhtear Uddin , KC Santosh , Chaowei Zhang , Xiao Qin , Yang Zhou

This article presents an agent architecture for controlling an autonomous agent in stochastic environments. The architecture combines the partially observable Markov decision process (POMDP) model with the belief-desire-intention (BDI)…

Artificial Intelligence · Computer Science 2016-07-05 Gavin Rens , Deshendran Moodley

Decentralized POMDPs provide an expressive framework for multi-agent sequential decision making. While fnite-horizon DECPOMDPs have enjoyed signifcant success, progress remains slow for the infnite-horizon case mainly due to the inherent…

Artificial Intelligence · Computer Science 2012-03-19 Akshat Kumar , Shlomo Zilberstein

Robotic imitation learning has achieved impressive success in learning complex manipulation behaviors from demonstrations. However, many existing robot learning methods do not explicitly account for the physical symmetries of robotic…

Robotics · Computer Science 2026-03-25 Zhiyuan Zhang , Aditya Mohan , Seungho Han , Wan Shou , Dongyi Wang , Yu She

We study the problem of achieving decentralized coordination by a group of strategic decision makers choosing to engage or not in a task in a stochastic setting. First, we define a class of symmetric utility games that encompass a broad…

Systems and Control · Electrical Eng. & Systems 2023-04-05 Marcos M. Vasconcelos , Behrouz Touri