Multi-Agent Coordination in Adversarial Environments through Signal Mediated Strategies

2021-02-09 · Federico Cacciamani, Andrea Celli, Marco Ciccone, Nicola Gatti

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 coordinate their strategies before the beginning of the game, but are unable to communicate during the playing phase of the game. This is the case, for example, in Bridge, collusion in poker, and collusion in bidding. In this setting, model-free RL methods are oftentimes unable to capture coordination because agents' policies are executed in a decentralized fashion. Our first contribution is a game-theoretic centralized training regimen to effectively perform trajectory sampling so as to foster team coordination. When team members can observe each other actions, we show that this approach provably yields equilibrium strategies. Then, we introduce a signaling-based framework to represent team coordinated strategies given a buffer of past experiences. Each team member's policy is parametrized as a neural network whose output is conditioned on a suitable exogenous signal, drawn from a learned probability distribution. By combining these two elements, we empirically show convergence to coordinated equilibria in cases where previous state-of-the-art multi-agent RL algorithms did not.

📄 PDF Abstract BibTeX arXiv:2102.05026

Code (0)

등록된 구현이 없습니다.

AdverSAR: Adversarial Search and Rescue via Multi-Agent Reinforcement Learning

2022-12-20 · Aowabin Rahman, Arnab Bhattacharya, Thiagarajan Ramachandran, Sayak Mukherjee 외

Search and Rescue (SAR) missions in remote environments often employ autonomous multi-robot systems that learn, plan, and execute a combination of local single-robot control actions, group primitives, and global mission-…

Meta-Learning Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning+1

Graph-Based Complexity Metrics for Multi-Agent Curriculum Learning: A Validated Approach to Task Ordering in Cooperative Coordination Environments

2025-07-09 · Farhaan Ebadulla, Dharini Hindlatti, Srinivaasan NS, Apoorva VH 외 arxiv

Multi-agent reinforcement learning (MARL) faces significant challenges in task sequencing and curriculum design, particularly for cooperative coordination scenarios. While curriculum learning has demonstrated success in …

Multi-agent Reinforcement Learning

Stateful active facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning

2022-10-04 · Dianbo Liu, Vedant Shah, Oussama Boussif, Cristian Meo 외

In cooperative multi-agent reinforcement learning, a team of agents works together to achieve a common goal. Different environments or tasks may require varying degrees of coordination among agents in order to achieve th…

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning (RL)

CoMIX: A Multi-agent Reinforcement Learning Training Architecture for Efficient Decentralized Coordination and Independent Decision-Making

2023-08-21 · Giovanni Minelli, Mirco Musolesi

Robust coordination skills enable agents to operate cohesively in shared environments, together towards a common goal and, ideally, individually without hindering each other's progress. To this end, this paper presents C…

Decision Making Multi-agent Reinforcement Learning

Do LLM-derived graph priors improve multi-agent coordination?

2026-04-19 · Nikunj Gupta, Rajgopal Kannan, Viktor Prasanna arxiv

Multi-agent reinforcement learning (MARL) is crucial for AI systems that operate collaboratively in distributed and adversarial settings, particularly in multi-domain operations (MDO). A central challenge in cooperative …

Multi-agent Reinforcement Learning Graph Neural Network