홈 › Papers

Mixed Cooperative-Competitive Communication Using Multi-Agent Reinforcement Learning

2021-10-29 · Astrid Vanneste, Wesley Van Wijnsberghe, Simon Vanneste, Kevin Mets, Siegfried Mercelis, Steven Latré, Peter Hellinckx

By using communication between multiple agents in multi-agent environments, one can reduce the effects of partial observability by combining one agent's observation with that of others in the same dynamic environment. While a lot of successful research has been done towards communication learning in cooperative settings, communication learning in mixed cooperative-competitive settings is also important and brings its own complexities such as the opposing team overhearing the communication. In this paper, we apply differentiable inter-agent learning (DIAL), designed for cooperative settings, to a mixed cooperative-competitive setting. We look at the difference in performance between communication that is private for a team and communication that can be overheard by the other team. Our research shows that communicating agents are able to achieve similar performance to fully observable agents after a given training period in our chosen environment. Overall, we find that sharing communication across teams results in decreased performance for the communicating team in comparison to results achieved with private communication.

📄 PDF Abstract BibTeX arXiv:2110.15762

Code (0)

등록된 구현이 없습니다.

Tasks

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

TarMAC: Targeted Multi-Agent Communication

2018-10-26 · ICLR 2019 5 · Abhishek Das, Théophile Gervet, Joshua Romoff, Dhruv Batra 외

We propose a targeted communication architecture for multi-agent reinforcement learning, where agents learn both what messages to send and whom to address them to while performing cooperative tasks in partially-observabl…

Multi-agent Reinforcement Learning Reinforcement Learning

Balancing Rational and Other-Regarding Preferences in Cooperative-Competitive Environments

2021-02-24 · Dmitry Ivanov, Vladimir Egorov, Aleksei Shpilman

Recent reinforcement learning studies extensively explore the interplay between cooperative and competitive behaviour in mixed environments. Unlike cooperative environments where agents strive towards a common goal, mixe…

Multi-agent Reinforcement Learning Q-Learning

On Emergent Communication in Competitive Multi-Agent Teams

2020-03-04 · Paul Pu Liang, Jeffrey Chen, Ruslan Salakhutdinov, Louis-Philippe Morency 외

Several recent works have found the emergence of grounded compositional language in the communication protocols developed by mostly cooperative multi-agent systems when learned end-to-end to maximize performance on a dow…

Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks

2018-12-23 · ICLR 2019 5 · Amanpreet Singh, Tushar Jain, Sainbayar Sukhbaatar

Learning when to communicate and doing that effectively is essential in multi-agent tasks. Recent works show that continuous communication allows efficient training with back-propagation in multi-agent scenarios, but hav…

Starcraft

Independent Natural Policy Gradient Always Converges in Markov Potential Games

2021-10-20 · Roy Fox, Stephen Mcaleer, Will Overman, Ioannis Panageas

Multi-agent reinforcement learning has been successfully applied to fully-cooperative and fully-competitive environments, but little is currently known about mixed cooperative/competitive environments. In this paper, we …

Multi-agent Reinforcement Learning