How many times I may walk over this super popular ML topic but it never ceases to amaze (or you may say scare me) with its ability to project itself to different spaces altogether. Let’s deconstruct and reconstruct this once again for one and all. Here’s a short introduction of... [Read More]

In this post, we will try to understand the basic mechanism behind genetic algorithm and use it to solve the reinforcement learning problem. See below how well genetic algorithm was able to balance cartpole in the 7th episode itself without using any gradient based strategy. Check out my solution on... [Read More]