Value-decomposition networks for cooperative multi-agent learning

P Sunehag, G Lever, A Gruslys, WM Czarnecki… - ar**_for_knowledge-based_multi-objective_multi-agent_reinforcement_learning/links/5cf8e03592851c4dd02c518a/Reward-sha**-for-knowledge-based-multi-objective-multi-agent-reinforcement-learning.pdf" data-clk="hl=it&sa=T&oi=gga&ct=gga&cd=1&d=13785574548084914414&ei=1TytZ87EA5bO6rQP6tvC0A0" data-clk-atid="7nhEKwMzUL8J" target="_blank">[PDF] researchgate.net

Reward sha** for knowledge-based multi-objective multi-agent reinforcement learning

P Mannion, S Devlin, J Duggan… - The Knowledge …, 2018 - cambridge.org
The majority of multi-agent reinforcement learning (MARL) implementations aim to optimize
systems with respect to a single objective, despite the fact that many real-world problems are …

Decentralized counterfactual value with threat detection for multi-agent reinforcement learning in mixed cooperative and competitive environments

S Dong, C Li, S Yang, W Li, Y Gao - Expert Systems with Applications, 2024 - Elsevier
This paper proposes a fully decentralized approach to address the challenge of general
mixed cooperation and competition within the domain of Multi-Agent Reinforcement …

Learning Aligned Local Evaluations For Better Credit Assignment In Cooperative Coevolution

J Cook, K Tumer - Proceedings of the Genetic and Evolutionary …, 2024 - dl.acm.org
Cooperative coevolutionary algorithms prove effective in solving tasks that can be easily
decoupled into subproblems. When applied to problems with high coupling (where the …

Leveraging Fitness Critics To Learn Robust Teamwork

J Cook, K Tumer, T Scheiner - Proceedings of the Genetic and …, 2023 - dl.acm.org
Co-evolutionary algorithms have successfully trained agent teams for tasks such as
autonomous exploration or robot soccer. However generally, such approaches seek a single …

Toll-based reinforcement learning for efficient equilibria in route choice

GO Ramos, BC Da Silva, R Rădulescu… - The Knowledge …, 2020 - cambridge.org
The problem of traffic congestion incurs numerous social and economical repercussions and
has thus become a central issue in every major city in the world. For this work we look at the …

Fitness sha** for multiple teams

J Cook, K Tumer - Proceedings of the Genetic and Evolutionary …, 2022 - dl.acm.org
Coevolutionary algorithms have effectively trained multiagent teams to collectively solve
complex problems. However, in many real-world applications, changes to the environment …

Maedys: Multiagent evolution via dynamic skill selection

E Sachdeva, S Khadka, S Majumdar… - Proceedings of the …, 2021 - dl.acm.org
Evolving effective coordination strategies in tightly coupled multi-agent settings with sparse
team fitness evaluations is challenging. It relies on multiple agents simultaneously stumbling …

Learning Individual Potential-Based Rewards in Multi-Agent Reinforcement Learning

C Yang, P Xu, J Zhang - IEEE Transactions on Games, 2024 - ieeexplore.ieee.org
A great challenge for applying multi-agent reinforcement learning (MARL) in the field of
game AI is to enable agents to learn diversified policies to handle different gamespecific …

Decoupled Monte Carlo Tree Search for Cooperative Multi-Agent Planning

O Asik, FB Aydemir, HL Akın - Applied Sciences, 2023 - mdpi.com
The number of agents exponentially increases the complexity of a cooperative multi-agent
planning problem. Decoupled planning is one of the viable approaches to reduce this …