About me

Hello there,

My name is Daniel Plop.

I am a computer scientist working on computational general-purpose learning agents. I hold a Bachelor’s degree in Computer Science (with a specialization in Games Engineering), and a Master’s degree in Computer Science (with a major in Machine Learning & Reinforcement Learning) from the Technical University of Munich (TUM).

This blog

Is an opportunity to share with others my ideas around robot psychology, software, and building learning agents for the exciting future we head toward. When it comes to robot psychology, I am most excited about reinforcement learning,

a computational approach to intelligence that focuses on the agent’s ability to achieve goals in its environment by trial-and-error learning.

As the definition suggests, reinforcement learning is an exceptionally general approach to developing goal-seeking agents. It makes few assumptions which are bound to the world we live in, therefore in principle, an implementation of such kind would be applicable to any world. The by far most important assumption it dares to make is

That all of what we mean by goals and purposes can be well thought of as maximization of the expected value of the cumulative sum of a received scalar signal (reward).1

Currently, I am particularly interested in building reinforcement learning agents for distributed markets.

Some past work

Reaching me

If you like to get in contact with me please include the phrase

somewhere in your first message to me so that I know you have read this page.

You can also find me on Github or Twitter.

  1. http://incompleteideas.net/rlai.cs.ualberta.ca/RLAI/rewardhypothesis.html ↩︎

  2. Denotes joint authorship. ↩︎