arXiv:2310.17416

Goals are Enough: Inducing AdHoc cooperation among unseen Multi-Agent systems in IMFs

Kaushik Dey, Satheesh K. Perepu, Abir Das

제출 2023-10-26

원문 초록

Intent-based management will play a critical role in achieving customers' expectations in the next-generation mobile networks. Traditional methods cannot perform efficient resource management since they tend to handle each expectation independently. Existing approaches, e.g., based on multi-agent reinforcement learning (MARL) allocate resources in an efficient fashion when there are conflicting expectations on the network slice. However, in reality, systems are often far more complex to be addressed by a standalone MARL formulation. Often there exists a hierarchical structure of intent fulfilment where multiple pre-trained, self-interested agents may need to be further orchestrated by a supervisor or controller agent. Such agents may arrive in the system adhoc, which then needs to be orchestrated along with other available agents. Retraining the whole system every time is often infeasible given the associated time and cost. Given the challenges, such adhoc coordination of pre-trained systems could be achieved through an intelligent supervisor agent which incentivizes pre-trained RL/MARL agents through sets of dynamic contracts (goals or bonuses) and encourages them to act as a cohesive unit towards fulfilling a global expectation. Some approaches use a rule-based supervisor agent and deploy the hierarchical constituent agents sequentially, based on human-coded rules. In the current work, we propose a framework whereby pre-trained agents can be orchestrated in parallel leveraging an AI-based supervisor agent. For this, we propose to use Adhoc-Teaming approaches which assign optimal goals to the MARL agents and incentivize them to exhibit certain desired behaviours. Results on the network emulator show that the proposed approach results in faster and improved fulfilment of expectations when compared to rule-based approaches and even generalizes to changes in environments.

함께 살펴볼 논문

공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.

arXiv:2606.26123v1cs.NI공통 태그 Management, Multi-agent Reinforcement Learning

6G SD-RAN에서 동적 VR 슬라이스 관리를 위한 프라이버시 인식 에이전트 협업

Privacy-Aware Agent Collaboration for Dynamic VR Slice Management in 6G SD-RAN

6G 네트워크에서 가상현실(VR) 서비스에는 초저지연과 높은 처리량이 필요하며, 이는 소프트웨어 정의 무선 액세스 네트워크(Software-Defined Radio Access Network, SD-RAN)의 동적 자원 관리에 중대한 과제를 제기한다. 본 연구는 VR 슬라이스 관리를 위한 이동성 기반, 프라이버시 인식 다중 에이전트 강화학습(Multi-Agent Reinforcement Learning, MARL) 프레임워크를 제안하며, 협력적 에이전트들이 사용자 데이터의 프라이버시를 보호하면서 end-to-end VR 링크 전반에 걸친 자원 분배를 최대화한다. 우리 접근법은 효과적이고 안전한 에이전트 협업을 촉진하기 위해 이동성 예측과 정보 병목(information bottleneck) 인코더를 통합한다. 시뮬레이션에서 전통적 방법과의 비교를 수행한 결과, 처리량이 최대 34% 향상되고, 자원 사용이 28% 감소하며, 프라이버시 유출이 85% 줄어들어, 미래 6G 환경에서 신뢰할 수 있는 몰입형 VR 경험을 보장한다.

토론

이 논문과 연결된 포럼 글이 아직 없습니다.