paper-with-me

홈 › Papers

Prism: Spectral Parameter Sharing for Multi-Agent Reinforcement Learning

2026-02-06 · Kyungbeom Kim, Seungwon Oh, Kyung-Joong Kim arxiv

Parameter sharing is a key strategy in multi-agent reinforcement learning (MARL) for improving scalability, yet conventional fully shared architectures often collapse into homogeneous behaviors. Recent methods introduce diversity through clustering, pruning, or masking, but typically compromise resource efficiency. We propose Prism, a parameter sharing framework that induces inter-agent diversity by representing shared networks in the spectral domain via singular value decomposition (SVD). All agents share the singular vector directions while learning distinct spectral masks on singular values. This mechanism encourages inter-agent diversity and preserves scalability. Extensive experiments on both homogeneous (LBF, SMACv2) and heterogeneous (MaMuJoCo) benchmarks show that Prism achieves competitive performance with superior resource efficiency.

📄 PDF Abstract BibTeX arXiv:2602.06476

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning

Similar Papers 제목 키워드 기반

PRISM: Complete Online Decentralized Multi-Agent Pathfinding with Rapid Information Sharing using Motion Constraints

2025-05-12 · Hannah Lee, Zachary Serlin, James Motes, Brendan Long 외

We introduce PRISM (Pathfinding with Rapid Information Sharing using Motion Constraints), a decentralized algorithm designed to address the multi-task multi-agent pathfinding (MT-MAPF) problem. PRISM enables large teams …

Benchmarking

Prism: Unleashing GPU Sharing for Cost-Efficient Multi-LLM Serving

2025-05-06 · Shan Yu, Jiarong Xing, Yifan Qiao, Mingyuan Ma 외

Serving large language models (LLMs) is expensive, especially for providers hosting many models, making cost reduction essential. The unique workload patterns of serving multiple LLMs (i.e., multi-LLM serving) create new…

GPUScheduling

PRISM: Position-encoded Regressive Inverse Spectral Model for Multilayer Thin-Film Design

2026-05-26 · Runtian Wang, Renhao Xue, Baige Chen, Hao Wu arxiv

The inverse problem of multilayer thin-film optical coatings design represents a complex combinatorial-continuous optimization challenge. We present PRISM (Position-encoded Regressive Inverse Spectral Model), a unified d…

PRIME: Blind Multispectral Unmixing Using Virtual Quantum Prism and Convex Geometry

2024-07-22 · Chia-Hsiang Lin, Jhao-Ting Lin

Multispectral unmixing (MU) is critical due to the inevitable mixed pixel phenomenon caused by the limited spatial resolution of typical multispectral images in remote sensing. However, MU mathematically corresponds to t…

blind source separation

PRISM: Structured Optimization via Anisotropic Spectral Shaping

2026-02-03 · Yujie Yang arxiv

We propose PRISM, an optimizer that enhances first-order spectral descent methods like Muon with partial second-order information. It constructs an efficient, low-rank quasi-second-order preconditioner via innovation-aug…