تقرير
Exploration via Epistemic Value Estimation
| العنوان: | Exploration via Epistemic Value Estimation |
|---|---|
| المؤلفون: | Schmitt, Simon, Shawe-Taylor, John, van Hasselt, Hado |
| سنة النشر: | 2023 |
| المجموعة: | Computer Science Statistics |
| مصطلحات موضوعية: | Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Statistics - Machine Learning |
| الوصف: | How to efficiently explore in reinforcement learning is an open problem. Many exploration algorithms employ the epistemic uncertainty of their own value predictions -- for instance to compute an exploration bonus or upper confidence bound. Unfortunately the required uncertainty is difficult to estimate in general with function approximation. We propose epistemic value estimation (EVE): a recipe that is compatible with sequential decision making and with neural network function approximators. It equips agents with a tractable posterior over all their parameters from which epistemic value uncertainty can be computed efficiently. We use the recipe to derive an epistemic Q-Learning agent and observe competitive performance on a series of benchmarks. Experiments confirm that the EVE recipe facilitates efficient exploration in hard exploration tasks. |
| نوع الوثيقة: | Working Paper |
| الوصول الحر: | http://arxiv.org/abs/2303.04012Test |
| رقم الانضمام: | edsarx.2303.04012 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |