Dear All,

You are cordially invited to the Brooklyn Quant Experience Lecture Series (BQE) on Thursday, February 6th at 6PM in LC 400, Dibner Building, 5 Metrotech Center – 4th Floor.

Dr. Dhruv Madeka who will present a talk on the following topic:

Title:

Practical Deep Reinforcement Learning

Abstract

We present a Deep Reinforcement Learning approach to solving a dynamic periodic review inventory system with stochastic vendor lead times, lost sales, correlated demand, and price matching. While this dynamic program has historically been considered intractable, we show that different policy learning approaches are competitive or outperform classical baseline policies. In order to train these algorithms, we develop techniques to convert historical data into off-policy data for a simulator.

Bio:

Dhruv Madeka is a Senior Machine Learning Scientist at Amazon. His current research focuses on applying Deep Reinforcement Learning to inventory management problems. Dhruv has also worked on developing generative and supervised deep learning models for probabilistic time series forecasting. In the past – Dhruv worked in the Quantitative Research team at Bloomberg LP, developing open source tools for the Jupyter Notebook and conducting advanced mathematical research in derivatives pricing, quantitative finance and election forecasting.

We look forward to having you join us for the talk and refreshments.