Importance Sampling with Unequal Support
Authors: Philip Thomas, Emma Brunskill
AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We applied US and IS to the problem of predicting the effectiveness of altering the treatment policy for a particular person with type 1 diabetes. ... For each value of CRmin (each of which corresponds to a value of c), we performed 2,433 trials, each of which involved generating the returns from 30 days... Figure 3 displays the bias, variance and mean squared error (MSE) of these 2,433 estimates, using an estimate of ground truth computed using Monte Carlo sampling. |
| Researcher Affiliation | Academia | Philip S. Thomas, Emma Brunskill {philipt,ebrun}@cs.cmu.edu Carnegie Mellon University |
| Pseudocode | No | The paper describes the US estimator mathematically in Equation (2) and explains its components, but it does not include a structured pseudocode block or a clearly labeled algorithm. |
| Open Source Code | No | The paper does not contain any statements or links indicating that the source code for the described methodology is publicly available. |
| Open Datasets | Yes | We used the subject Adult#003 in the Type 1 Diabetes Metabolic Simulator (T1DMS) (Dalla Man et al. 2014) a simulator that has been approved by the US Food and Drug Administration as a substitute for animal trials in pre-clinical testing of treatment policies for type 1 diabetes. |
| Dataset Splits | No | The paper describes generating data using a simulator for 2,433 trials, each involving 30 days of data. It does not specify fixed training, validation, or test dataset splits in the conventional sense, as data is simulated on the fly for each trial. |
| Hardware Specification | No | The paper states that experiments were performed on an 'in silico person' simulated using T1DMS, but it does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used to run these simulations. |
| Software Dependencies | No | The paper mentions using the 'Type 1 Diabetes Metabolic Simulator (T1DMS) (Dalla Man et al. 2014)', but it does not specify a version number for this simulator or any other software dependencies. |
| Experiment Setup | Yes | The treatment policy is parameterized by two numbers, CR and CF... After analyzing the performance of many CR and CF pairs, we selected an initial range that results in good performance: CR [8.5, 11] and CF [10, 15]... CR is sampled from the truncated normal distribution over [CRmin, 11], with mean 11 and standard deviation 11 CRmin. |