Multi-Agent Hide and Seek
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: https://openai.com/blog/emergent-tool-use/
Видео Multi-Agent Hide and Seek канала OpenAI
Learn more: https://openai.com/blog/emergent-tool-use/
Видео Multi-Agent Hide and Seek канала OpenAI
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Simulating Natural SelectionI Made the Hardest Game EverNeural network racing cars around a trackOpenAI Plays Hide and Seek…and Breaks The Game! 🤖This AI Does Nothing In Games…And Still Wins!AI vs. AI. Two chatbots talking to each otherAI Learns to Park - Deep Reinforcement LearningAI Learns to Steal BananasAI Learns To Survive4 Experiments Where the AI Outsmarted Its Creators 🤖I Made a Zero Player GameSimulating Foraging DecisionsI Made a Game with Intentional Bugs¡Esta IA juega al ESCONDITE demasiado bien!Simulating the Evolution of AggressionMarI/O - Machine Learning for Video GamesThe Trouble With TumbleweedOpenAI Five Beats World Champion DOTA2 Team 2-0AlphaGo - The Movie | Full Documentary