This work proposes HiGFRL, a Hierarchical Graph Fusion-Driven Reinforcement Learning framework, which designs a fusion-driven dual-network architecture to optimize RL decision-making and incorporates a topology-prior-guided hybrid reward mechanism that distills static topological priors into the learning process to accelerate convergence.
Abstract
Online scheduling of dependency-aware tasks in heterogeneous cloud clusters is a fundamental yet challenging problem due to the complex interplay between DAG topologies and multi-dimensional resource constraints. While DRL has shown promise, existing GNN-based approaches often struggle to efficiently model high-order topological dependencies and suffer from loose coupling between task and resource states, leading to myopic scheduling decisions. To address these limitations, we propose HiGFRL, a Hierarchical Graph Fusion-Driven Reinforcement Learning framework. HiGFRL constructs a novel three-level state representation comprising a Static Hypergraph, a Dynamic Global Graph, and a Local Bipartite Graph to explicitly model the interplay between task dependencies and real-time cluster dynamics. Specifically, we design a fusion-driven dual-network architecture to optimize RL decision-making, where a Context Fusion Allocator integrates local bipartite matching features with fused global context to execute precise task-to-node allocation, and a Global State Evaluator leverages the global dynamic graph representation to accurately estimate expected long-term cumulative reward. Furthermore, we incorporate a topology-prior-guided hybrid reward mechanism that distills static topological priors into the learning process to accelerate convergence. Extensive experiments using real-world Alibaba cluster traces demonstrate that HiGFRL significantly outperforms heuristics and DRL baselines. Specifically, in challenging large-scale high-load scenarios, HiGFRL reduces the Makespan by up to 32.55%, and optimizes the average task flow time and average task wait time by 13.58% and 13.79%, respectively. Experimental results confirm that HiGFRL not only significantly improves cluster throughput but also ensures superior QoS by substantially reducing queuing delays. Code Release:https://github.com/igeng/HiGFRL.
A Graph Attention-Driven Hierarchical Reinforcement Learning framework is developed and model the scheduling process as an event-driven hierarchical semi-Markov decision process (SMDP) that maintains competitive workflow success rate and generally achieves higher container utilization and lower energy consumption.
Zong-Jin Li, Shaohan Feng, Chun-Xi Yang et al.· 0 citations
HRL-TaskOpt is presented, a novel Hierarchical Reinforcement Learning-based task scheduling framework that combines high-level global task offloading with millisecond-granularity local scheduling policies in an edge–cloud scenario and offers a scalable and intelligent solution for adaptive task scheduling.
Krishna Patwari, Raghvendra Kumar, J. Sastry· International Journal of Ele...· 0 citations
ReLA is an RL scheduler built on structured representation learning and aggregation that learns intra-entity representations using self-attention and convolution, captures inter-entity operation–machine interactions using cross-attention, and aggregates multi-scale representations for parallel actor-based scoring of fe...
Zheng-Yi Kwan, Wei Zhang, Aik Beng Ng et al.· International Conference on...· 0 citations
Experimental results demonstrate that DRG-MAPPO achieves a state-of-the-art win rate of 87%, suggesting that the framework effectively balances relational modeling, interpretability, and optimization stability for cooperative air combat.
Junlin Liu, Cheng-Wei Li, Yang Gao et al.· 0 citations
The spatial-temporal mismatch between generation and load is exacerbated by high distributed photovoltaic (PV) penetration in distribution service areas, causing power quality degradation and PV accommodation challenges. To tackle this issue, an end-to-end optimal scheduling method based on a heterogeneous graph attent...
Wei Zheng, Han Yan, Jin-Gang Qin et al.· Journal of Renewable and Sus...· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026