Alejandro AristizabalinTowards Data ScienceUnderstanding Reinforcement Learning Hands-On: The Bellman Equation pt.1Understanding how an agent evaluates an environmentOct 19, 2020Oct 19, 2020
Alejandro AristizabalinTowards Data ScienceUnderstanding Reinforcement Learning Hands-On: Markov Decision ProcessesDescribing and understanding complex environments, one diagram at a time.Sep 30, 2020Sep 30, 2020
Alejandro AristizabalinTowards Data ScienceUnderstanding Reinforcement Learning Hands-on: Non-StationarityDealing with a dynamic world is not an easy task. In this third article on a series on RL, we present strategies for non-stationarity…Sep 14, 2020Sep 14, 2020
Alejandro AristizabalinTowards Data ScienceUnderstanding Reinforcement Learning Hands-On: Multi-Armed BanditsThis is the second entry of a series on Reinforcement Learning, where we explore the armed-bandit problem and the Explore-exploit dilemma…Sep 7, 2020Sep 7, 2020
Alejandro AristizabalinTowards Data ScienceUnderstanding Reinforcement Learning Hands-On: IntroductionThis is the first article on a series on Reinforcement Learning , where we explore the ideas behind RL, both from theory and applications…Aug 31, 2020Aug 31, 2020
Alejandro AristizabalinTowards Data ScienceMaking PATE Bidirectionally PrivatePATE, or Private Aggregation of Teacher Ensembles, is a machine learning framework proposed by Papernot et al. in the paper…Aug 20, 2019Aug 20, 2019