OpenAI Bot Minecraft 70,000 Hours Footage
OpenAI wanted to advance artificial intelligence (AI) and machine learning research in a more creative way, so they trained their new bot to play Minecraft using over 70,000 hours of gameplay footage from YouTube. The bot utilized the gameplay actions and tutorials to learn how to execute complex in-game sequences that would take a normal player around 24,000 individual actions to accomplish.



Their behavioral cloning model accomplished many tasks including learning how to chop down trees to collect logs and then craft those into planks. It doesn’t stop there, the bot then crafts those planks into a crafting table. This sequence would typically take a human Minecraft player approximately 50 seconds or 1,000 consecutive game actions.

ASUS TUF Dash 15 (2022) Gaming Laptop, 15.6" 144Hz FHD Display, Intel Core i7-12650H, GeForce RTX 3060,...
  • SUPERCHARGED RTX GRAPHICS - Gameplay graphics are silky smooth with the NVIDIA GeForce RTX 3060 6GB GDDR6 at 1050W with Dynamic Boost, with...
  • MUX SWITCH BOOST - A MUX Switch lets the GPU communicate directly with the display, increasing performance and decreasing latency
  • READY FOR ANYTHING - Use your gaming laptop to stream and multi-task with ease thanks to an Intel Core i7-12650H Processor with 24MB Cache, up to 4.7...

OpenAI Bot Minecraft 70,000 Hours Footage

Additionally, the model performs other complex skills humans often do in the game, such as swimming, hunting animals for food, and eating that food. It also learned the skill of ‘pillar jumping’, a common behavior in Minecraft of elevating yourself by repeatedly jumping and placing a block underneath yourself,” said the researchers.

Author

A technology, gadget and video game enthusiast that loves covering the latest industry news. Favorite trade show? Mobile World Congress in Barcelona.