Skip to content

seanrsinclair/hindsight-learning

Repository files navigation

Hindsight Learning in MDPs with Exogenous Inputs

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

This code implements and evaluates algorithms for the paper Hindsight Learning for MDPs with Exogenous Inputs . In this paper we introduce Hindsight Learning, an algorithm to learn efficiently in a sub-class of MDPs coined MDPs with Exogenous Inputs.

@inproceedings{sinclair2023hindsight,
  title={Hindsight Learning in MDPs with Exogenous Inputs},
  author={Sinclair, Sean R. and Frujeri, Felipe  and Cheng, Ching-An and Marshall, Luke and Barbalho, Hugo and Li, Jingling and Neville, Jennifer and Menache, Ishai and Swaminathan, Adith},
  booktitle={arXiv},
  year={2023},
}

This project is licensed under the terms of the MIT license.

Repository Overview

The code is subdivided into three folders for the three different experiments conducted, including:

  • Online Bin Packing (OBP)
  • Airline Revenue Management (ARM)
  • Multi Secretary (MS)

The Virtual Machine (VM) Allocation code is proprietary and thus is not included in the supplementary materials.

Contributing

Contact srs429@cornell.edu to contribute.

About

Hindsight Learning for MDPs with Exogenous Inputs

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published