#openai#reinforcementlearning#multi-agent
2.1M subscribers • 3 videos on Hallway
Beginner. No background in the topic needed.
11M views7 years ago1 recommendation
AI and machine learningReinforcement learningAI agents and tool use
OpenAI demonstrates how artificial agents playing hide-and-seek evolve complex strategies and counter-strategies, including emergent tool use, through multi-agent reinforcement learning.
We’ve observed agents discovering progressively more complex tool use while playing a simple game of hide-and-seek. Through training in our new simulated hide-and-seek environment, agents build a series of six distinct strategies and counterstrategies, some of which we did not know our environment supported. The self-supervised emergent complexity in this simple environment further suggests that multi-agent co-adaptation may one day produce extremely complex and intelligent behavior. Learn more: openai.com/blog/emergent-tool-use/What people say. Recommended as a fascinating demonstration of emergent behaviors and complex strategy development in multi-agent reinforcement learning environments.
aeternumon Hacker News • Recommends
On “Experts who say we shouldn't worry about superintelligent AI are wrong?”
willhkon Hacker News • Mentions
On “Dota 2 with Large Scale Deep Reinforcement Learning [pdf]”
ShamelessCon Hacker News • Mentions
On “What Does It Mean for AI to Understand?”
HaukeHion Hacker News • Mentions
On “It looks like you’re trying to take over the world”
treesprite82on Hacker News • Mentions
On “Forget the hype, “thinking machines” can’t replace humans”
PartiallyTypedon Hacker News • Mentions
On “On Device Learning”
HanClintoon Hacker News • Mentions
On “Prover-Verifier Games improve legibility of language model outputs”