zr-obp

zr-obp copied to clipboard

Online simulator with drift and delays

8

Note: This MR is an adaptation of #176 based on the suggestions in https://github.com/st-tech/zr-obp/pull/176#issuecomment-1192528581 ## Why As an applied researcher on applications of bandits, I want to be able to...

Braamling

Add factual rewards to synthetic data generation and enable online bandit simulations

6

### Why As an applied researcher on applications of bandits, I want to be able to compare various bandits algorithms in simulation. ### About the change The current implementation of...

Braamling

Bumps [numpy](https://github.com/numpy/numpy) from 1.21.2 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...

dependabot[bot]

Wrong parameter set in fig.add_subplot() in OffPolicyEvaluation.visualize_off_policy_estimates_of_multiple_policies

2

Isn't the parameter for this part `len(self.ope_estimators_)` instead of `len(action_dist_list)` ? With the current code, I think that the output image will not be normal unless `len(self.ope_estimators_)` and `len(action_dist_list)` are...

MotoShin

Add new github actions

1

## Motivation This issue summarizes the github actions that we plan to introduce in the future. Please feel free to leave comments. ## TODOs - [x] [flake8](https://github.com/PyCQA/flake8) (or [hacking](https://github.com/openstack/hacking)) -...

nomuramasahir0

The current Read the Docs is not the latest version, so it seems that it needs to be modified. In fact, the following contents are inconsistent. * https://zr-obp.readthedocs.io/en/latest/_autosummary/obp.dataset.base.html#module-obp.dataset.base https://github.com/st-tech/zr-obp/blob/01aef32b898b2f523fcc7f64e7b48eb1ffc59b04/obp/dataset/base.py#L8-L14 If...

nomuramasahir0

# Possible Issue In bandit feedback, n_actions are set as ```int(self.action.max() + 1)```, which doesn't raise any error in above code, assuming that logs generated by ```policy``` covered all possible...

yoongi0428

propensity score estimate

2

Hello, In the input dataset, propensity scores needs to be provided, does the the propensity score needs to be calibrated ? How is the impact of wrong propensity score ?...

arita37

Is it possible some hard-coded setup in generic functions like BernoulliTS sampler ? example: Specifix Zozotown dataset params are hard coded (!) for campaign params Suppose one want to use...

arita37

Bumps [joblib](https://github.com/joblib/joblib) from 1.0.1 to 1.2.0. Changelog Sourced from joblib's changelog. Release 1.2.0 Fix a security issue where eval(pre_dispatch) could potentially run arbitrary code. Now only basic numerics are supported....

dependabot[bot]