English

Towards Data-Driven Offline Simulations for Online Reinforcement Learning

Machine Learning 2022-11-15 v1

Abstract

Modern decision-making systems, from robots to web recommendation engines, are expected to adapt: to user preferences, changing circumstances or even new tasks. Yet, it is still uncommon to deploy a dynamically learning agent (rather than a fixed policy) to a production system, as it's perceived as unsafe. Using historical data to reason about learning algorithms, similar to offline policy evaluation (OPE) applied to fixed policies, could help practitioners evaluate and ultimately deploy such adaptive agents to production. In this work, we formalize offline learner simulation (OLS) for reinforcement learning (RL) and propose a novel evaluation protocol that measures both fidelity and efficiency of the simulation. For environments with complex high-dimensional observations, we propose a semi-parametric approach that leverages recent advances in latent state discovery in order to achieve accurate and efficient offline simulations. In preliminary experiments, we show the advantage of our approach compared to fully non-parametric baselines. The code to reproduce these experiments will be made available at https://github.com/microsoft/rl-offline-simulation.

Keywords

Cite

@article{arxiv.2211.07614,
  title  = {Towards Data-Driven Offline Simulations for Online Reinforcement Learning},
  author = {Shengpu Tang and Felipe Vieira Frujeri and Dipendra Misra and Alex Lamb and John Langford and Paul Mineiro and Sebastian Kochman},
  journal= {arXiv preprint arXiv:2211.07614},
  year   = {2022}
}

Comments

Presented at the 3rd Offline Reinforcement Learning Workshop at NeurIPS 2022

R2 v1 2026-06-28T05:50:17.003Z