AI Olympics (multi-agent reinforcement learning)

AI Warehouse · Beginner ·🤖 AI Agents & Automation ·2y ago

Skills: RL Foundations80%Multi-Agent Systems70%

AI Competes in a 100m Dash! In this video 5 AI Warehouse agents compete to learn how to run 100m the fastest. The AI were 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. Each agent's actions are controlled by a Neural Network that's updated after each attempt in order to try to give the agents more rewards and less punishments over time. Check the pinned comment for more information on how the AI was trained! Current Subscribers: 264,870

Watch on YouTube ↗ (saves to browser)

Sign in to unlock AI tutor explanation · ⚡30

Playlist

Uploads from AI Warehouse · AI Warehouse · 5 of 20

← Previous Next →

AI Agent Learns to Escape (deep reinforcement learning)

AI Agent Learns to Escape (deep reinforcement learning)

AI Agent Learns to Escape (deep reinforcement learning)

AI Agent Learns to Escape (deep reinforcement learning)

AI Learns to Walk (deep reinforcement learning)

AI Learns to Walk (deep reinforcement learning)

AI Olympics (multi-agent reinforcement learning)

AI Olympics (multi-agent reinforcement learning)

AI Olympics - 100m Race #ai #deeplearning

AI Olympics - 100m Race #ai #deeplearning

AI learns to walk, in a weird way... #ai #neuralnetworks #aiwarehouse

AI learns to walk, in a weird way... #ai #neuralnetworks #aiwarehouse

Humanoid AI vs Stairs (deep reinforcement learning)

Humanoid AI vs Stairs (deep reinforcement learning)

AI Learns Insane Way to Jump

AI Learns Insane Way to Jump

AI vs. AI Fight

AI vs. AI Fight

AI Learns to Play Tag (and breaks the game)

AI Learns to Play Tag (and breaks the game)

AI Learns to Dodge #ai #deeplearning #aiwarehouse

AI Learns to Dodge #ai #deeplearning #aiwarehouse

1v10 AI Dodgeball (deep reinforcement learning)

1v10 AI Dodgeball (deep reinforcement learning)

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

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

AI Learns to Escape Extreme Maze

AI Learns to Escape Extreme Maze

AI Learns to Play Soccer (and breaks physics)

AI Learns to Play Soccer (and breaks physics)

AI Learns Red Light Green Light (reinforcement learning)

AI Learns Red Light Green Light (reinforcement learning)

AI Learns to Fight Uncut (deep reinforcement learning)

AI Learns to Fight Uncut (deep reinforcement learning)

AI Learns to Sumo Wrestle (deep reinforcement learning)

AI Learns to Sumo Wrestle (deep reinforcement learning)

AI Learns to Race Hurdles (deep reinforcement learning)

AI Learns to Race Hurdles (deep reinforcement learning)

More on: RL Foundations

View skill →

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

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

Nicholas Renotte

Deep Reinforcement Learning for Atari Games Python Tutorial | AI Plays Space Invaders

Deep Reinforcement Learning for Atari Games Python Tutorial | AI Plays Space Invaders

Nicholas Renotte

Training & Testing Deep reinforcement learning (DQN) Agent - Reinforcement Learning p.6

Training & Testing Deep reinforcement learning (DQN) Agent - Reinforcement Learning p.6

Build a Game Bot (LIVE)

Build a Game Bot (LIVE)

How to Win Slot Machines - Intro to Deep Learning #13

How to Win Slot Machines - Intro to Deep Learning #13

Build an Mario AI Model with Python | Gaming Reinforcement Learning

Build an Mario AI Model with Python | Gaming Reinforcement Learning

Nicholas Renotte

Related AI Lessons

LearnCurator - I built a YouTube tutorial search engine that filters videos, ranks by AI‑analysed comments

Build a YouTube tutorial search engine that filters videos and ranks them by AI-analyzed comments to save time and improve learning

i ran frontier ai entirely on my own hardware for months, and i can't go back

Run AI models locally on your own hardware for more control and efficiency, and explore the possibilities of local artificial intelligence

Unit Economics of an AI-Operated Business: £20 £17.97 Revenue in 72 Hours (Real Numbers)

Learn how to calculate unit economics for an AI-operated business and apply it to your own startup with real numbers and examples

I built Codemate — a multi-agent coding assistant with memory and mistake learning

Learn how Codemate, a multi-agent coding assistant, improves AI coding workflows with memory and mistake learning

Strands Agents SDK, an agentic framework that helps you build custom agents.