Solving Hierarchical Information-Sharing Dec-POMDPs: An Extensive-Form Game Approach
원문 초록
A recent theory shows that a multi-player decentralized partially observable Markov decision process can be transformed into an equivalent single-player game, enabling the application of \citeauthor{bellman}'s principle of optimality to solve the single-player game by breaking it down into single-stage subgames. However, this approach entangles the decision variables of all players at each single-stage subgame, resulting in backups with a double-exponential complexity. This paper demonstrates how to disentangle these decision variables while maintaining optimality under hierarchical information sharing, a prominent management style in our society. To achieve this, we apply the principle of optimality to solve any single-stage subgame by breaking it down further into smaller subgames, enabling us to make single-player decisions at a time. Our approach reveals that extensive-form games always exist with solutions to a single-stage subgame, significantly reducing time complexity. Our experimental results show that the algorithms leveraging these findings can scale up to much larger multi-player games without compromising optimality.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
skfolio: Portfolio Optimization in Python
100-Day Analysis of USD/IDR Exchange Rate Dynamics Around the 2025 U.S. Presidential Inauguration
Automated Risk Management Mechanisms in DeFi Lending Protocols: A Crosschain Comparative Analysis of Aave and Compound
Semantic Scheduling for LLM Inference
SDialog: A Python Toolkit for Synthetic Dialogue Generation and Analysis
From Axioms to Algorithms: Mechanized Proofs of the vNM Utility Theorem
토론
이 논문과 연결된 포럼 글이 아직 없습니다.