Reinforcement Learning Courses and Certifications

Yannic Kilcher

Fast Reinforcement Learning With Generalized Policy Updates - Paper Explained

Explore reinforcement learning and policy updates with Yannic Kilcher in under an hour. Learn to carry over knowledge from previous tasks to new ones, even creating zero-shot policies.

• YouTube
• 55 minutes
• On-Demand
• Free Online Course

Aleksa Gordić - The AI Epiphany

MuZero - Mastering Atari, Go, Chess, and Shogi by Planning with a Learned Model - RL Paper Explained

Understand MuZero, the latest agent in the AlphaGo lineage, with Aleksa Gordić's AI Epiphany. Learn how it plays without rules and achieves state-of-the-art results on Atari benchmark in under an hour.

• YouTube
• 28 minutes
• On-Demand
• Free Online Course

Aleksa Gordić - The AI Epiphany

OpenAI - Solving Rubik's Cube with a Robot Hand - RL Paper Explained

Explore OpenAI's robotic hand simulation that solves Rubik's cube in under an hour with The AI Epiphany's Aleksa Gordić.

• YouTube
• 55 minutes
• On-Demand
• Free Online Course

Aleksa Gordić - The AI Epiphany

DeepMind's AlphaGo Zero and AlphaZero - RL Paper Explained

Understand AlphaGo Zero and AlphaZero, AI agents that mastered Go, Chess, and Shogi through self-play, in less than an hour with Aleksa Gordić.

• YouTube
• 42 minutes
• On-Demand
• Free Online Course

Edan Meyer

This AI Learns from YouTube

Edan Meyer's brief study on OpenAI's paper about training an AI to play Minecraft using imitation and reinforcement learning, with a focus on semi-supervised learning.

• YouTube
• 21 minutes
• On-Demand
• Free Online Course

Edan Meyer

Learning Fast with No Goals - VISR Explained

Edan Meyer's brief study on VISR, a DeepMind paper on rapid task adaptation in Reinforcement Learning, focusing on successor features and goal-conditioned policies.

• YouTube
• 36 minutes
• On-Demand
• Free Online Course

Edan Meyer

Reinforcement Learning in RTS Games

Explore reinforcement learning in RTS games with Edan Meyer's concise study, covering key insights from recent research papers. Less than 1-hour workload.

• YouTube
• 23 minutes
• On-Demand
• Free Online Course

Edan Meyer

Agent Learns to Do Reinforcement Learning

Explore reinforcement learning with Edan Meyer in less than an hour. Understand algorithm distillation, behavior cloning, and their implications for the future.

• YouTube
• 25 minutes
• On-Demand
• Free Online Course

Nicholas Renotte

Custom Indicators for Reinforcement Learning Trading Tutorial - GME Python Trading PT2

Learn to create custom financial indicators for a Python Reinforcement Learning bot with Nicholas Renotte. In under an hour, master trading Gamestop stocks using RSI, SMA, and OBV indicators.

• YouTube
• 29 minutes
• On-Demand
• Free Online Course

Nicholas Renotte

Reinforcement Learning for Trading Tutorial - GME RL Python Trading

Learn to build a Python Trading Bot using Reinforcement Learning with Gamestop stock prices in less than an hour with Nicholas Renotte.

• YouTube
• 38 minutes
• On-Demand
• Free Online Course

Nicholas Renotte

Python Reinforcement Learning Tutorial for Beginners

Learn to create an OpenAI gym environment and train a reinforcement learning algorithm in Python with Nicholas Renotte in under an hour.

• YouTube
• 26 minutes
• On-Demand
• Free Online Course

Nicholas Renotte

Build a Street Fighter AI Model with Python - Gaming Reinforcement Learning Full Course

Learn to build a Street Fighter AI model using Python with Nicholas Renotte. Master Gym Retro setup, hyperparameter tuning, and model fine-tuning in 2-3 hours.

• YouTube
• 2 hours 41 minutes
• On-Demand
• Free Online Course

Nicholas Renotte

Build a Doom AI Model with Python - Gaming Reinforcement Learning Full Course

Learn to build a Doom AI model using Python with Nicholas Renotte. Master VizDoom installation, OpenAI Gym, Stable Baselines 3, and improve results with Curriculum Learning and Reward Shaping.

• YouTube
• 3 hours 17 minutes
• On-Demand
• Free Online Course

Nicholas Renotte

Build a Mario AI Model with Python - Gaming Reinforcement Learning

Learn to build an AI model to play Super Mario using Python and reinforcement learning in this 1-2 hour tutorial by Nicholas Renotte.

• YouTube
• 1 hour 17 minutes
• On-Demand
• Free Online Course

Nicholas Renotte

Reinforcement Learning - Full Course Using Python

Learn reinforcement learning fundamentals with Python, OpenAI Gym, and Stable Baselines in a 3-4 hour program by Nicholas Renotte. Build deep learning agents to solve RL problems.

• YouTube
• 3 hours 2 minutes
• On-Demand
• Free Online Course