Practical Considerations in Reinforcement Learning and Bayesian Modeling

Data Science Philadelphia (DataPhilly)
Data Science Philadelphia (DataPhilly)
Public group

LeBow College of Business

3220 Market Street · Philadelphia

How to find us

We will meet in Room 031 in the lower level of LeBow hall

Location image of event venue


Learning Deep Reinforcement Learning - by Scott Rome

Deep Reinforcement Learning sounds intractable for a layperson. "Reinforcement learning" alone sounds scary (I'm reinforcing WHAT again? Random actions? Bah!), and then you add the word "deep" and most people simply drop off. This talk details what I've learned from replicating the original NIPS/Nature papers on Deep Reinforcement Learning for playing Atari games and walks through some python implementations of the basic steps for reinforcement learning code. The talk uses Keras (TensorFlow backend) and tries (albeit, unsuccessfully) to hide advanced mathematical formulations of the problem. By the end of the talk, we will all have taken a modest step forward in learning deep reinforcement learning. About the Speaker: Scott is the lead data scientist at Cadent, which is a local television advertising company. He is particularly interested in practical applications of deep learning models. He holds a PhD in applied mathematics from Drexel University

Two Years of Bayesian Bandits for E-Commerce - by Austin Rochford

At Monetate, we've deployed Bayesian bandits (both noncontextual and contextual) to help our clients optimize their e-commerce sites since early 2016. This talk is an overview of the lessons we've learned from both the processes of deploying real-time Bayesian machine learning systems at scale and building a data product on top of these systems that is accessible to non-technical users (marketers). This talk will cover

• The place of multi-armed bandits in the A/B testing industry,
• Thompson sampling and the basic theory of Bayesian bandits,
• Bayesian approaches for accommodating nonstationarity in bandit feedback,
• User experience challenges in driving adoption of these technologies by nontechnical marketers.

We will focus primarily on noncontextual bandits and give a brief overview of these problems in the contextual setting as time permits.

About the Speaker: Austin Rochford is a Principal Data Scientist and Director of Monetate Labs. He is a founding member of Monetate Labs, where he does research and development for machine learning-driven marketing products. He is a recovering mathematician, a passionate Bayesian, and a PyMC3 developer.

Thank you to Drexel LeBow’s Business Analytics Solutions Center ( for hosting us

Drexel LeBow’s Business Analytics Solutions Center is a hub for collaboration between academia and industry, providing business solutions for organizations through faculty and student analytics consulting teams, thought leadership, and industry recognition.