My first experience with deep reinforcement learning

Image from http://ai.berkeley.edu

Now, for the project…

From the results that DeepMind published in one of its papers, one of the graphs looked like this:

Comparison of DeepMind's DQN with the best reinforcement learning algorithms in the literature [1]

The experience

I had a lot of fun with this project, but what’s more, I learned a lot. Now, from my experience, I think reinforcement learning has the potential to be very powerful, especially in combination with neural networks. However, this combination is what can make the process a little frustrating if you are expecting your model to learn in a matter of a couple of hours and then win every game you play against it. The reality is that neural networks, while very powerful, can require very fine tuning to actually learn something. But more than this, you have to be very careful, for example, with the parameters you choose, the topology, and the activation functions as some of these aspects can represent the difference between a neural network that does a very good job in a reasonable time and a neural network that doesn’t learn anything. In summary, getting a good model can require many optimizations and dedication, however when you achieve one the results can be very surprising (as groups like DeepMind have shown us).

Finally, why PacMan?

Since it’s a game I really like — I mean, who doesn’t?


AI Society

Artificial Intelligence Hacking Group

Thanks to Juan Camilo Bages Prada and Esteban Vargas.

Diego Montoya Sefair

Written by

AI Society

Artificial Intelligence Hacking Group