This work applies multi-agent actor-critic and multi-agent attention-actor-critic approaches – off-policy multi-agent re-inforcement learning (MARL) approaches – in the MARL imitation learning inner loop, as opposed to MACK – the on-policy MARL method used in MAGAIL.
This work proposes MAFIS, a novel method that addresses limitations for both online and offline MAIL settings by building upon the single-agent IQ-Learn framework and introducing the value decomposition network to factorize the imitation objective at agent level, thus enabling scalable training for multi-agent systems.
Yichen Li, Zhongxiang Ling, Tao Jiang et al.· Neural Information Processin...· 3 citations
A comparative study of shared-experience multi-agent extensions of multi-agent actor-critic methods for parameterized action reinforcement learning, offering insight into the scalability of shared-experience multi-agent actor-critic methods for parameterized action reinforcement learning.
U. Bapoo, Clement N. Nyirenda· arXiv.org· 0 citations
This paper presents a narrative survey of recent developments in MARL and examines research directions centred on centralised training with decentralised execution (CTDE), value decomposition, learned communication, graph-based methods, and model-based learning.
Abdur Rakib, Khoa Phung, Marco Pérez Hernández et al.· Applied Sciences· 0 citations
This work proposes Agentic-DPO, a lightweight offline agent policy optimization method that turns expert trajectories into state-conditioned preference supervision, and introduces Policy-Preserving Augmentation (PPA), which renders the same latent trajectory under multiple schemas while keeping the expert policy fixed.
This paper introduces Multi-AGent Preference-Integrated lEarning (MAGPIE), a framework that leverages agent-specific preference signals in the multi-agent learning process and can derive Nash equilibrium solutions.
Ni Mu, Yao Luan, Yiqin Yang et al.· IEEE Transactions on Automat...· 0 citations
The proposed method, which extends previous work on controllability in multi-agent deep reinforcement learning, enables uninstructed agents to adaptively complement overlooked tasks and areas and enables uninstructed agents to implicitly complement the overall work based on the actions of other agents.
Y. Takahagi, Gentoku Nakasone, Yoshinari Motokawa et al.· 2025 IEEE/WIC International...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
