A curated list of research papers, code, and tools applying deep reinforcement learning (DRL) to cloud/microservice resource scheduling and autoscaling.

Implementation of a toy scheduling problem (2 machines, 4 tasks) with classical baselines and QUBO/Ising encoding as the foundation for exploring quantum optimization approaches.

RL-powered cloud job scheduler that minimises carbon footprint — tier-pool routing, real-time energy data, and LLM explainability

Companion artefact for the DRL-for-cloud-scheduling production-oriented survey: executed DeepRM proof-of-concept benchmark (code + per-seed results), industry-deployment evidence, survey scope, and frozen bibliography.