Off-Policy Evaluation for Large Action Spaces via Embeddings. (arXiv:2202.06317v2 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/2202.06317

Off-policy evaluation (OPE) in contextual bandits has seen rapid adoption in
real-world systems, since it enables offline evaluation of new policies using
only historic log data. Unfortunately, when the number of actions is large,
existing OPE estimators -- most of which are based on inverse propensity score
weighting -- degrade severely and can suffer from extreme bias and variance.
This foils the use of OPE in many applications from recommender systems to
language models. To overcome this issue, we propose …

arxiv evaluation lg policy