COIN: Chance-Constrained Imitation Learning for Uncertainty-aware Adaptive Resource Oversubscription Policy
On the map: Offline RL and imitation learning from data → Offline RL algorithms
Abstract (arXiv)
We address the challenge of learning safe and robust decision policies in presence of uncertainty in context of the real scientific problem of adaptive resource oversubscription to enhance resource efficiency while ensuring safety against resource congestion risk. Traditional supervised prediction or forecasting models are ineffective in learning adaptive policies whereas standard online optimization or reinforcement learning is difficult to deploy on real systems. Offline methods such as imitation learning (IL) are ideal since we can directly leverage historical resource usage telemetry. But, the underlying aleatoric uncertainty in such telemetry is a critical bottleneck. We solve this with our proposed novel chance-constrained imitation learning framework, which ensures implicit safety against uncertainty in a principled manner via a combination of stochastic (chance) constraints on resource congestion risk and ensemble value functions. This leads to substantial (≈ 3-4×) improvement in resource efficiency and safety in many oversubscription scenarios, including resource management in cloud services.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Offline RL algorithms, one of 13 directions in Offline RL and imitation learning from data. Builds on 19 of its 46 references that are in the map. First posted on arXiv 13 Jan 2024.
Builds on
19 of 46 references.
References · 19
- 2015Continuous control with deep reinforcement learningcited by 3,279
- 2017Constrained Policy Optimizationcited by 928
- 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
- 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 813
- 2019Causal Confusion in Imitation Learningcited by 286
- 2018Safe Exploration in Continuous Action Spacescited by 237
- 2020Reinforcement Learning for Combinatorial Optimization: A Surveycited by 235
- 2019Constrained Reinforcement Learning Has Zero Duality Gapcited by 144
- 2018EnsembleDAgger: A Bayesian Approach to Safe Imitation Learningcited by 96
- 2020Serverless in the Wild: Characterizing and Optimizing the Serverless Workload at a Large Cloud Providercited by 65
- 2020Constrained Markov Decision Processes via Backward Value Functionscited by 33
- 2019Uncertainty-Aware Data Aggregation for Deep Imitation Learningcited by 19
7 more
- 2021Model-based Chance-Constrained Reinforcement Learning via Separated Proportional-Integral Lagrangiancited by 13
- 2019Uncertainty-Aware Imitation Learning using Kernelized Movement Primitivescited by 11
- 2020Model-Based Actor-Critic with Chance Constraint for Stochastic Systemcited by 9
- 2020Prediction-Based Power Oversubscription in Cloud Platformscited by 6
- 2017Overcommitment in Cloud Services -- Bin packing with Chance Constraintscited by 5
- 2014On Cloud-based Oversubscriptioncited by 2
- 2018Reinforcement Learning for Resource Provisioning in Vehicular Cloudcited by 2
Built on by
Citing papers per year: 2025: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025RISE: Robust Imitation through Stochastic Encoding
- 2026Distributionally Robust and Safe Imitation Learning
- 2023Balancing policy constraint and ensemble size in uncertainty-based offline reinforcement learning
- 2025Learning safe, constrained policies via imitation learning: Connection to Probabilistic Inference and a Naive Algorithm
- 2021An Offline Risk-aware Policy Selection Method for Bayesian Markov Decision Processes
- 2024Diffusion Policies for Risk-Averse Behavior Modeling in Offline Reinforcement Learning
- 2021Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism
- 2020Expert-Supervised Reinforcement Learning for Offline Policy Learning and Evaluation