AI Olympics (multi-agent reinforcement learning)
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
▶︎
1v10 AI Dodgeball (deep reinforcement learning)
▶︎
AI Learns Red Light Green Light (reinforcement learning)
▶︎
I Made an Evolution Simulator (with silly little guys)
▶︎
Simulating the Evolution of Aggression
▶︎
AI learns to beat a crazy map
▶︎
Beckbros React To The AI Olympics!
▶︎
AI Learns to Exploit a Glitch in a Racing Game
▶︎
AI Learns to Race Hurdles (deep reinforcement learning)
▶︎
10 AIs Play Among Us
▶︎
AI Learns to Play Tag (and breaks the game)
▶︎
Reacting to AI Learning Red Light Green Light
▶︎
HIPPO MARBLE Race Destroys 99.22% of Marbles! - Marble World
▶︎
Evolving AIs - Predator vs Prey, who will win?
▶︎
AI Agent Learns to Escape (deep reinforcement learning)
▶︎
If Toy Story was a tower defense game...
▶︎
I Trained an AI Until It Mastered Physics
▶︎
AI Learns to Escape the Abandoned Lab (Reinforcement Learning)
▶︎
AI Learns to Run Faster than Usain Bolt | World Record
▶︎
I Forced 5 AIs to Work Together...(it was bad)
▶︎
AI Learns to Play Soccer (and breaks physics)
▶︎
AI Learns to Escape the Lab (Inspired by AI Warehouse)
▶︎
I Trained an AI to Beat This Absurd World Record
▶︎
I Forced 10 AIs to play Among Us...(it was bad)
▶︎