Overcoming Sparse Rewards in Reinforcement Learning

Overcoming Sparse Rewards in Reinforcement Learning

This video, a follow up from his intro video on reinforcement learning, Arxiv dives into three advanced papers that address the problem of the sparse... Details
Mathematics of Dopamine

Mathematics of Dopamine

In this video, Siraj Raval explores how key reinforcement learning algorithms help explain how the human brain works, specifically through the lens of the neurotransmitter known... Details
Comparing Humans with the Best Reinforcement Learning Algorithms

Comparing Humans with the Best Reinforcement Learning Algorithms

By leveraging powerful prior knowledge about how the world works, humans can quickly figure out efficient strategies in new and unseen environments. Currently, even state-of-the-art... Details
Q Learning for Trading

Q Learning for Trading

Siraj Raval explores the world of automated training with reinforcement learning with a few lines of Python code! In this video, he demonstrates how a... Details
DeepMind AlphaGo Zero Explained

DeepMind AlphaGo Zero Explained

If you're a reader of this blog, then you know that I have mentioned Alpha Go Zero before on a few occasions. However, I think... Details
How an AI Learns Dexterity

How an AI Learns Dexterity

The folks over at OpenAI have come up with some very interesting work in training robots on improving their dexterity via reinforcement learning. Their robot, Dactyl, has... Details
How Does AlphaGo Zero Work?

How Does AlphaGo Zero Work?

I just wrapped up a new article for my AI column in MSDN Magazine on reinforcement learning. AlphaGo Zero was a key example of RL's... Details
How Deepmind’s AlphaZero Can Master Games Without Human Knowledge

How Deepmind’s AlphaZero Can Master Games Without Human Knowledge

If my post yesterday about DeepMind's AlphaZero piqued your interest but answered too few questions, then check out this video from teh 2017 NIPS conference where Dr.... Details
How AlphaGo Zero Taught Itself to Be a Go Master

How AlphaGo Zero Taught Itself to Be a Go Master

First, AlphaGo beat the best human player in the world by studying thousands of human vs. human games. Then AlphaGo Zero came along and taught... Details
An introduction to Reinforcement Learning

An introduction to Reinforcement Learning

Here's an interesting look at one of the most promising fields in AI today: Reinforcement Learning. I just completed the Reinforcement Learning certification on EdX and... Details