AI Learns to Play Dodgeball! #ai #deeplearning #aiwarehouse

AI Warehouse · Beginner ·📐 ML Fundamentals ·1y ago
AI learns to play Dodgeball In this video an AI Warehouse agent named Albert learns to play Dodgeball against Kai. The AI was trained using Deep Reinforcement Learning, a method of Machine Learning which involves rewarding the agent for doing something correctly, and punishing it for doing anything incorrectly. Albert's actions are controlled by a Neural Network that's updated after each attempt in order to try to give Albert more rewards and less punishments over time. Check the related video for more information on how the AI was trained!
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related AI Lessons

Paper Insights: Sobolev Training
Learn about Sobolev Training, a research topic in Physics-Informed Machine Learning (PIML), and its potential applications
Medium · Machine Learning
When Climate Is a Residual, You’re Pricing for a Past That No Longer Exists
Learn how causal machine learning reveals climate risk in mortgage credit models and why it matters for pricing
Medium · Machine Learning
L2 Distance was Giving Me Wrong Answers. Here’s the Metric That Fixed it.
Learn how to choose the right distance metric for your data science problem and avoid incorrect results
Medium · Data Science
From Correlation to Causation
Learn to distinguish between correlation and causation in machine learning to make more accurate predictions and understand the underlying reasons for patterns in data
Medium · Machine Learning
Up next
Advanced Data Structures and Problem-Solving Techniques
Coursera
Watch →