Get the latest Science News and Discoveries
SharpeRatio@k: novel metric for evaluation of risk-return tradeoff in off-policy evaluation - EurekAlert
<p><strong>SharpeRatio@k, a novel evaluation metric for Off-Policy Evaluation estimators, effectively measures the risk-return tradeoff of evaluating policies used in reinforcement learning</strong> <strong>and contextual bandits, which are typically ignored by conventional metrics, show scientists at Tokyo Tech. This novel metric, inspired from risk assessment in financial portfolio management, provides a more insightful evaluation of OPE, paving the way for improved policy selection.</strong></p>
None
Or read this on Eureka Alert