Matches in SemOpenAlex for { <https://semopenalex.org/work/W3157205593> ?p ?o ?g. }
- W3157205593 abstract "When faced with sequential decision-making problems, it is often useful to be able to predict what would happen if decisions were made using a new policy. Those predictions must often be based on data collected under some previously used decision-making rule. Many previous methods enable such off-policy (or counterfactual) estimation of the expected value of a performance measure called the return. In this paper, we take the first steps towards a universal off-policy estimator (UnO) -- one that provides off-policy estimates and high-confidence bounds for any parameter of the return distribution. We use UnO for estimating and simultaneously bounding the mean, variance, quantiles/median, inter-quantile range, CVaR, and the entire cumulative distribution of returns. Finally, we also discuss Uno's applicability in various settings, including fully observable, partially observable (i.e., with unobserved confounders), Markovian, non-Markovian, stationary, smoothly non-stationary, and discrete distribution shifts." @default.
- W3157205593 created "2021-05-10" @default.
- W3157205593 creator A5034701757 @default.
- W3157205593 creator A5043572737 @default.
- W3157205593 creator A5045674062 @default.
- W3157205593 creator A5066332280 @default.
- W3157205593 creator A5073570605 @default.
- W3157205593 creator A5084989076 @default.
- W3157205593 date "2021-04-26" @default.
- W3157205593 modified "2023-10-12" @default.
- W3157205593 title "Universal Off-Policy Evaluation" @default.
- W3157205593 cites W1095970959 @default.
- W3157205593 cites W1514587017 @default.
- W3157205593 cites W1536719639 @default.
- W3157205593 cites W1541084404 @default.
- W3157205593 cites W1557189666 @default.
- W3157205593 cites W156410395 @default.
- W3157205593 cites W1581437610 @default.
- W3157205593 cites W1591803298 @default.
- W3157205593 cites W1867103660 @default.
- W3157205593 cites W1963965317 @default.
- W3157205593 cites W1992154527 @default.
- W3157205593 cites W2025533349 @default.
- W3157205593 cites W2026774322 @default.
- W3157205593 cites W2033436114 @default.
- W3157205593 cites W2085126194 @default.
- W3157205593 cites W2090346540 @default.
- W3157205593 cites W2093272448 @default.
- W3157205593 cites W2097345597 @default.
- W3157205593 cites W2102288976 @default.
- W3157205593 cites W2108026887 @default.
- W3157205593 cites W2109415218 @default.
- W3157205593 cites W2110065044 @default.
- W3157205593 cites W2120575449 @default.
- W3157205593 cites W2120678009 @default.
- W3157205593 cites W2121863487 @default.
- W3157205593 cites W2124515734 @default.
- W3157205593 cites W2129995532 @default.
- W3157205593 cites W2132527237 @default.
- W3157205593 cites W2134359669 @default.
- W3157205593 cites W2149418961 @default.
- W3157205593 cites W2275802500 @default.
- W3157205593 cites W2313791856 @default.
- W3157205593 cites W2356031020 @default.
- W3157205593 cites W2568411832 @default.
- W3157205593 cites W2605323209 @default.
- W3157205593 cites W2708031219 @default.
- W3157205593 cites W2739473244 @default.
- W3157205593 cites W2751325639 @default.
- W3157205593 cites W2765302304 @default.
- W3157205593 cites W2788086877 @default.
- W3157205593 cites W2797563284 @default.
- W3157205593 cites W2799825833 @default.
- W3157205593 cites W2803308811 @default.
- W3157205593 cites W2807306981 @default.
- W3157205593 cites W2945269249 @default.
- W3157205593 cites W2945850894 @default.
- W3157205593 cites W2948416696 @default.
- W3157205593 cites W2962802563 @default.
- W3157205593 cites W2970971581 @default.
- W3157205593 cites W2991598122 @default.
- W3157205593 cites W2998059334 @default.
- W3157205593 cites W2998548529 @default.
- W3157205593 cites W2999778183 @default.
- W3157205593 cites W3000543388 @default.
- W3157205593 cites W3005930619 @default.
- W3157205593 cites W3009007264 @default.
- W3157205593 cites W3011515502 @default.
- W3157205593 cites W3013430759 @default.
- W3157205593 cites W3024294996 @default.
- W3157205593 cites W3034525128 @default.
- W3157205593 cites W3035307445 @default.
- W3157205593 cites W3035670794 @default.
- W3157205593 cites W3035901905 @default.
- W3157205593 cites W3036236109 @default.
- W3157205593 cites W3044620414 @default.
- W3157205593 cites W3045055178 @default.
- W3157205593 cites W3045923282 @default.
- W3157205593 cites W3049337243 @default.
- W3157205593 cites W3081008408 @default.
- W3157205593 cites W3082245592 @default.
- W3157205593 cites W3085145582 @default.
- W3157205593 cites W3091826069 @default.
- W3157205593 cites W3092398080 @default.
- W3157205593 cites W3093731986 @default.
- W3157205593 cites W3094117125 @default.
- W3157205593 cites W3112404509 @default.
- W3157205593 cites W3117215073 @default.
- W3157205593 cites W3155071387 @default.
- W3157205593 cites W567721252 @default.
- W3157205593 cites W2951873965 @default.
- W3157205593 hasPublicationYear "2021" @default.
- W3157205593 type Work @default.
- W3157205593 sameAs 3157205593 @default.
- W3157205593 citedByCount "3" @default.
- W3157205593 countsByYear W31572055932021 @default.
- W3157205593 crossrefType "posted-content" @default.
- W3157205593 hasAuthorship W3157205593A5034701757 @default.
- W3157205593 hasAuthorship W3157205593A5043572737 @default.
- W3157205593 hasAuthorship W3157205593A5045674062 @default.