An Introduction to Reinforcement Learning – III :: Dynamic Programming Applications to the OpenAI Gym

Welcome back to my series of articles on Reinforcement Learning, where I stumble through and try and understand RL, and hopefully convey some useful knowledge along the way. In the first article, I talked about the basic terminology and concepts and ultimately introduced Markov Decision Processes (MDPs). In the second article in the series, the […]

Read More An Introduction to Reinforcement Learning – III :: Dynamic Programming Applications to the OpenAI Gym

An Introduction to Reinforcement Learning – II :: Dynamic Programming

1. Introduction We started talking about the basics of reinforcement learning (RL) in the last post. Here, we will talk about and implement some dynamic programming (DP) solutions for certain Markov Decision Processes (MDP) where the model is completely known. We will initially motivate why we need dynamic programming for this problem, and then go […]

Read More An Introduction to Reinforcement Learning – II :: Dynamic Programming

An Introduction to Reinforcement Learning – I :: Markov Decision Processes

1. Introduction The best way to understand something is to try and explain it. And if you keep getting better every time you try to explain it, well, that’s roughly the gist of what Reinforcement Learning (RL) is about.  Given how different RL is from Supervised or Unsupervised Learning, I figured that the best strategy is […]

Read More An Introduction to Reinforcement Learning – I :: Markov Decision Processes

De-biasing word embeddings using spaCy

1. Introduction The Distributional Hypothesis, formulated by Zellig Harris in 1954, talks about the fact that words that occur in similar contexts tend to have similar meanings. This eventually led to the rise of the field of Distributional Semantics, a field which mostly deals with “theories and methods for quantifying and categorizing semantic similarities between linguistic […]

Read More De-biasing word embeddings using spaCy

Rise of the Chatbots – I :: A basic Chatbot using Rasa, which queries the Spotify API, using Slack as a frontend

1. Introduction Chatbots are in. They have been for awhile. They can be controversial, as suggested by Tay’s plight in 2016, or they can be confusing and spark panic in the general public, as Facebook found out last year, with rumors of its chatbots ‘talking to each other’ widely circulating in the media. They can […]

Read More Rise of the Chatbots – I :: A basic Chatbot using Rasa, which queries the Spotify API, using Slack as a frontend

Creating Dadaist Poetry using Python and NLTK :: I. Just the Basics

The Dada movement is fascinating. An anti-establishment, avant-garde, principally European art movement, one of its main goals (rooted in the pre-World War I anti-art movement) was to challenge the accepted notions of what art was, and what it symbolized. Marcel Duchamp’s Fountain (1917), shown below, remains one of the most iconic pieces of art that […]

Read More Creating Dadaist Poetry using Python and NLTK :: I. Just the Basics

Galaxy Clusters and Machine Learning – I :: Creating Mock Cluster Catalogs

1. Introduction I’ll start this post with the same line that pretty much any paper or article on galaxy clusters ever begins with: Galaxy clusters are the the most massive, gravitationally bound systems in the universe. These gigantic objects comprise galaxies (from a few hundreds to the order of thousands) held together by gravity. Clusters […]

Read More Galaxy Clusters and Machine Learning – I :: Creating Mock Cluster Catalogs