Only H is left: Near-tight Episodic PAC RL
Authors:
NeurIPS 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on benchmark datasets for different classification algorithms demonstrate the method and the resulting reduction in churn. (...) (V) empirical analysis of the proposed methods on benchmark datasets with different classification algorithms. (...) This section demonstrates the churn reduction effect of the RCP operator for three UCI benchmark datasets (see Table 2) with three regression algorithms. |
| Researcher Affiliation | Collaboration | Q. Cormier ENS Lyon 15 parvis René Descartes Lyon, France quentin.cormier@ens-lyon.fr (...) M. Milani Fard, K. Canini, M. R. Gupta Google Inc. 1600 Amphitheatre Parkway Mountain View, CA 94043 {mmilanifard,canini,mayagupta}@google.com |
| Pseudocode | No | The paper describes methods and equations but does not present any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any statement or link indicating the availability of open-source code for the described methodology. |
| Open Datasets | Yes | This section demonstrates the churn reduction effect of the RCP operator for three UCI benchmark datasets (see Table 2) (...) Table 2: Description of the datasets used in the experimental analysis. Nomao [13] News Popularity [14] Twitter Buzz [15] |
| Dataset Splits | Yes | We randomly split each dataset into three fixed parts: a training set, a validation set on which we optimized the hyper-parameters for all algorithms, and a testing set. (...) Validation set 1000 samples (for each dataset in Table 2). |
| Hardware Specification | No | The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper states that the regression algorithms were 'all implemented in Scikit-Learn [12]', but it does not specify a version number for Scikit-Learn, which is necessary for reproducibility. |
| Experiment Setup | Yes | We impute any missing values by the corresponding mean, and normalize the data to have zero mean and variance 1 on the training set. (...) We run the MCMC chain for k = 30 steps (...) The dataset perturbation sub-samples 80% of the examples in TA and randomly drops 3-7 features. (...) We used fixed values of α = 0.5 and ϵ = 0.5 for all the experiments in Table 3. |