babaniyi/deep-contextual-bandits

A benchmark to test decision-making algorithms for contextual-bandits. The library implements a variety of algorithms (many of them based on approximate Bayesian Neural Networks and Thompson sampling), and a number of real and syntethic data problems exhibiting a diverse set of properties.

Deep Contextual Bandits

This library corresponds to the Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Sampling paper, published in ICLR 2018. The authors provide a benchmark to test decision-making algorithms for contextual-bandits. In particular, the current library implements a variety of algorithms (many of them based on approximate Bayesian Neural Networks and Thompson sampling), and a number of real and syntethic data problems exhibiting a diverse set of properties.

It is a Python library that uses TensorFlow. The TensorFlow archive directory of the paper is located here.

Goal

The codes are not maintained anymore and I intend to create a package that allows it to work on any dataset.

deep-contextual-bandits's Issues

tensorboard.plugins.hparams error

I have followed below and obtained another error, “ TypeError: HParam.init() got an unexpected keyword argument 'num_actions'”

from tensorboard.plugins.hparams import api as hp

Then you can instantiate the parameters as:
hp.HParam(num_actions = num_actions)