Prism: Spectral Parameter Sharing for Multi-Agent Reinforcement Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Multi-agent Reinforcement LearningSimilar Papers 제목 키워드 기반
PRISM: Complete Online Decentralized Multi-Agent Pathfinding with Rapid Information Sharing using Motion Constraints
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 …
BenchmarkingPrism: Unleashing GPU Sharing for Cost-Efficient Multi-LLM Serving
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…
GPUSchedulingPRISM: Position-encoded Regressive Inverse Spectral Model for Multilayer Thin-Film Design
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
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 separationPRISM: Structured Optimization via Anisotropic Spectral Shaping
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…