Representation Learning For Efficient Deep Multi-agent Reinforcement Learning

Abstract

Sample efficiency remains a key challenge in multi-agent reinforcement learning (MARL). A promising approach is to learn a meaningful latent representation space through auxiliary learning objectives alongside the MARL objective to aid in learning a successful control policy. In our work, we present MAPO-LSO (Multi-Agent Policy Optimization with Latent Space Optimization) which applies a form of comprehensive representation learning devised to supplement MARL training. Specifically, MAPO-LSO proposes a multi-agent extension of transition dynamics reconstruction and self-predictive learning that constructs a latent state optimization scheme that can be trivially extended to current state-of-the-art MARL algorithms. Empirical results demonstrate MAPO-LSO to show notable improvements in sample efficiency and learning performance compared to its vanilla MARL counterpart without any additional MARL hyperparameter tuning on a diverse suite of MARL tasks.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhuh2024representation

Related papers

• End-to-end Optimization Of Llm-driven Multi-agent Search Systems Via Heterogeneous-group-based Reinforcement Learning (2025)0.00
• Low-rank Agent-specific Adaptation (lorasa) For Multi-agent Policy Learning (2025)0.00
• Offline Multi-agent Reinforcement Learning Via In-sample Sequential Policy Optimization (2024)0.00
• Model-based Multi-agent Policy Optimization With Adaptive Opponent-wise Rollouts (2021)0.00
• Multi-agent Constrained Policy Optimisation (2021)0.00
• MABL: Bi-level Latent-variable World Model For Sample-efficient Multi-agent Reinforcement Learning (2023)0.00
• Heterogeneous Multi-agent Reinforcement Learning For Zero-shot Scalable Collaboration (2024)6.34
• Simplifying Model-based RL: Learning Representations, Latent-space Models, And Policies With One Objective (2022)0.00