Creating a Policy Gradient (PG) Agent to Trade
Creating Neural Networks with Python/Keras/Tensorflow to Predict the Future
Asynchronous Advantage Actor Critic (A3C)-Reinforcement Learning -Laymens Explanation
The A3C method in Reinforcement Learning (RL) combines both a critic’s value function (how good a state is) and an actor’s policy (a set of action probability for a given state). I promise this explanation doesn’t not contain greek letters or calculus. It only contains English alphabets and subtraction in...
[Read More]
React Redux Intro
I’ve been bugged by the native state management system in React that I finally had to take a stab at Redux. Here are some notes I took along the way to understand what Redux is and why we need it.
[Read More]