paper-with-me

Papers

Hindsight Learning for MDPs with Exogenous Inputs

2022-07-13 · Sean R. Sinclair, Felipe Frujeri, Ching-An Cheng, Luke Marshall, Hugo Barbalho, Jingling Li, Jennifer Neville, Ishai Menache, Adith Swaminathan

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.

📄 PDF Abstract BibTeX arXiv:2207.06272

Code (1)

seanrsinclair/hindsight-learning 공식 구현

Tasks

counterfactualDecision MakingDecision Making Under UncertaintyManagementReinforcement Learning (RL)Sequential Decision Making

Similar Papers 제목 키워드 기반

Is Pure Exploitation Sufficient in Exogenous MDPs with Linear Function Approximation?

2026-01-28 · Hao Liang, Jiayu Cheng, Sean R. Sinclair, Yali Du arxiv

Exogenous MDPs (Exo-MDPs) capture sequential decision-making where uncertainty comes solely from exogenous inputs that evolve independently of the learner's actions. This structure is especially common in operations rese…

Exploiting Exogenous Structure for Sample-Efficient Reinforcement Learning

2024-09-22 · Jia Wan, Sean R. Sinclair, Devavrat Shah, Martin J. Wainwright

We study Exo-MDPs, a structured class of Markov Decision Processes (MDPs) where the state space is partitioned into exogenous and endogenous components. Exogenous states evolve stochastically, independent of the agent's …

reinforcement-learningReinforcement Learning

Learning in POMDPs is Sample-Efficient with Hindsight Observability

2023-01-31 · Jonathan N. Lee, Alekh Agarwal, Christoph Dann, Tong Zhang

POMDPs capture a broad class of decision making problems, but hardness results suggest that learning is intractable even in simple settings due to the inherent partial observability. However, in many realistic problems, …

Decision MakingScheduling

Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight

2023-07-06 · Jiacheng Guo, Minshuo Chen, Huan Wang, Caiming Xiong 외

This paper studies the sample-efficiency of learning in Partially Observable Markov Decision Processes (POMDPs), a challenging problem in reinforcement learning that is known to be exponentially hard in the worst-case. M…

Dynamical-VAE-based Hindsight to Learn the Causal Dynamics of Factored-POMDPs

2024-11-12 · Chao Han, Debabrota Basu, Michael Mangan, Eleni Vasilaki 외

Learning representations of underlying environmental dynamics from partial observations is a critical challenge in machine learning. In the context of Partially Observable Markov Decision Processes (POMDPs), state repres…