Reinforcement Learning Video 3

This is video 3 of a three part series on temporal difference methods and reinforcement learning

[@vijtad]

Explained to the point without going too deep into math that any one can understand. Please continue videos for bandits, TD lambda and Game theory.

[@MrAndreaCaso]

You explained q-learning in 20 minutes, showing the practical implementation of it. I do not understand why tutorials do not do exactly what you did before getting down to the maths. Once the basics of implementation and the intuition are clear the maths become clearer too, even when it's complicated. Well done. Please continue on publishing videos. Why don't you start a Patreon account?