Light

roycoding / slots Goto Github PK

View Code? Open in Web Editor NEW

81.0 5.0 22.0 191 KB

A multi-armed bandit library for Python

License: MIT License

Python 100.00%

multi-armed-bandit python

slots's People

Contributors

Stargazers

Watchers

slots's Issues

Record regret values in an attribute array based on input parameter

Fix `true_divide` `RuntimeWarning`

slots.py:377: RuntimeWarning: invalid value encountered in true_divide sum(self.pulls) * np.max(np.nan_to_num(self.wins / self.pulls))

Drop Python 2.7 and 3.4 support

Remove explicit support for Python 2.7 and 3.4

Ability to save regret values after each trial in an array

Add tests

We need tests!

I am planning to use pytest.
Asymptotic tests would be nice for the MAB strategies.

Add type hints

Fix instantiation of n arms for online trials

Refactor for fixed and variable payouts

Refactor to historical and future payouts for both fixed payout values (both binary and numerical) and variable payouts.

For live trials, handle binary or numerical payouts.
For off-line trials, handle fixed binary or numerical payouts and variable numerical payouts.

This probably requires a relatively significant API change.

Optionally add current regret to the online response

Inline variable attribution type hints are breaking 3.5 compatibility

Options:

Refactor type hints for 3.5 compatibility
Remove 3.5 support

Python 3.7 support

Python 3.6 support

Basic defaults results in an error

Running

mab = slots.MAB()
mab.run()

results in an error.

This seems to be due to how the defaults are handled for a "live" trial.

live=False might be a better default?

Limit trial history to N pulls to limit memory usage

Does the current Bayesian bandit strategy work for non-binary payouts?

I want to be sure that the current implementation of the Bayesian bandits works if the payouts are arbitrary sizes, rather than just the default 0 or 1.

Separate out strategies into separate file

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.