# Hindsight Learning for MDPs with Exogenous Inputs

Source: [Hindsight Learning for MDPs with Exogenous Inputs](<https://www.sota2.com/research/paper/68fa70f41e209131cea4e637>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:54:43.381Z

Authors: Sean R. Sinclair, Felipe Frujeri, Ching-An Cheng, Luke Marshall, Hugo Barbalho, Jingling Li, Jennifer Neville, Ishai Menache, Adith Swaminathan

Published: 2022-07-13T15:18:00.000Z

## Abstract

Many resource management problems require sequential decision-making under uncertainty, where the only uncertainty affecting the decision outcomes are exogenous variables outside the control of the decision-maker. We model these problems as Exo-MDPs (Markov Decision Processes with Exogenous Inputs) and design a class of data-efficient algorithms for them termed Hindsight Learning (HL). Our HL algorithms achieve data efficiency by leveraging a key insight: having samples of the exogenous variables, past decisions can be revisited in hindsight to infer counterfactual consequences that can accelerate policy improvements. We compare HL against classic baselines in the multi-secretary and airline revenue management problems. We also scale our algorithms to a business-critical cloud resource management problem -- allocating Virtual Machines (VMs) to physical machines, and simulate their performance with real datasets from a large public cloud provider. We find that HL algorithms outperform domain-specific heuristics, as well as state-of-the-art reinforcement learning methods.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [VM Scheduling on Huawei-East-1 (train)](<https://www.sota2.com/research/sota/vm-scheduling-on-huawei-east-1-train.md>): VM Scheduling; Huawei-East-1 (train); Performance Ratio (S1): 99.9.

- [VM Scheduling on Azure (train)](<https://www.sota2.com/research/sota/vm-scheduling-on-azure-train.md>): VM Scheduling; Azure (train); Mean Score: 62.8.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2207.06272>)

[PDF](<https://arxiv.org/pdf/2207.06272.pdf>)