Towards Data-Driven Offline Simulations for Online Reinforcement Learning

November 14, 2022 ยท Entered Twilight ยท ๐Ÿ› arXiv.org

๐Ÿ’ค TWILIGHT: Eternal Rest
Repo abandoned since publication

Repo contents: .flake8, .github, .gitignore, CODE_OF_CONDUCT.md, LICENSE, README.md, SECURITY.md, SUPPORT.md, examples, offsim4rl, requirements.txt, setup.py, tests

Authors Shengpu Tang, Felipe Vieira Frujeri, Dipendra Misra, Alex Lamb, John Langford, Paul Mineiro, Sebastian Kochman arXiv ID 2211.07614 Category cs.LG: Machine Learning Citations 1 Venue arXiv.org Repository https://github.com/microsoft/rl-offline-simulation โญ 31 Last Checked 3 months ago
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning