FUMA'S REINFORCEMENT LEARNING HUT

for those who dare to fail

Welcome to Fuma's Reinforcement Learning Hut!
I'm passionate about optimization and strongly believe Neural Networks will change the world.
This is my hut, a familiar place of discovery and learning where I'll share my findings for those interested in Reinforcement Learning, both in theory and practice.

Home: Welcome

Fuma

Apr 6, 20211 min read

Implementing a Linear Regression & Multi-Armed Bandit

I'm currently following this course on Udemy: https://www.udemy.com/course/artificial-intelligence-reinforcement-learning-in-python/...

Fuma

Apr 6, 20211 min read

Commented code for solving CartPole-v1 with Policy Gradient and a simple Neural Network policy

A commented, Colab-compatible version of an implementation of a Neural Network Policy to solve OpenAI gym's CartPole-v1 using Policy...

Fuma

Mar 20, 20213 min read

Policy Optimization Algorithm: the maths behind REINFORCE and its gradient calculation

Hello everyone! I've seen courses that begun by explaining Tabular RL first, getting into Value-based RL, but I think starting from...

Fuma

Mar 6, 20213 min read

A Map of Reinforcement Learning Algorithms

Despite the usefulness of this wonderful subject, there is a scarcity on the web of accurate RL Algorithms maps. The best ones I've been...

Fuma

Feb 19, 20212 min read

UC Berkeley CS 285 series & other resources I draw from

I'm currently following University of California's Computer Science 285 classes, which can be found at this address:...

Home: Blog2

FUMA'S REINFORCEMENT LEARNING HUT

Implementing a Linear Regression & Multi-Armed Bandit

Commented code for solving CartPole-v1 with Policy Gradient and a simple Neural Network policy

Policy Optimization Algorithm: the maths behind REINFORCE and its gradient calculation

A Map of Reinforcement Learning Algorithms

UC Berkeley CS 285 series & other resources I draw from

Subscribe Form