Emergent tool use from multi-agent interaction - OpenAI
Sep 17, 2019 · In our environment, agents play a team-based hide-and-seek game. Hiders (blue) are tasked with avoiding line-of-sight from the seekers (red), and seekers are tasked with keeping vision of the hiders.
Multi-Agent Hide and Seek - YouTube
Sep 17, 2019 · OpenAI. 1.28M subscribers. Subscribed. 155K. 10M views 5 years ago. We’ve observed agents discovering progressively more complex tool use while playing a simple game of hide-and-seek. Through...
AI learned to use tools after nearly 500 million games of hide and seek
Sep 17, 2019 · Through playing a simple game of hide and seek hundreds of millions of times, two opposing teams of AI agents developed complex hiding and seeking strategies that involved tool use and...
AI Hide and Seek: Agents Punched Holes in their Creators' Universe
Sep 19, 2019 · Two teams of AI agents tasked with playing a game (or million) of hide and seek in a virtual environment developed complex strategies and counterstrategies – and exploited holes in their environment that even its creators didn’t even know that it had.
An AI learned to play hide-and-seek. The strategies it came up …
Sep 20, 2019 · This week, leading AI lab OpenAI released their latest project: an AI that can play hide-and-seek. It’s the latest example of how, with current machine learning techniques, a very simple...
[1909.07528] Emergent Tool Use From Multi-Agent Autocurricula
Sep 17, 2019 · Through multi-agent competition, the simple objective of hide-and-seek, and standard reinforcement learning algorithms at scale, we find that agents create a self-supervised autocurriculum inducing multiple distinct rounds of emergent strategy, many of which require sophisticated tool use and coordination. We find clear evidence of six emergent ...
GitHub - FarkadAdnan/Hide-and-Seek: Through multi-agent …
Hide-and-Seek. Through multi-agent competition, the simple goal of hide-and-seek and standardized augmentative learning algorithms on a large scale, we find that agents create a self-supervised approach that catalyses multiple distinct rounds of emerging strategy, many of which require sophisticated use and coordination of the tool.
openai/multi-agent-emergence-environments - GitHub
Hide and seek - mae_envs/envs/hide_and_seek.py - The Hide and Seek environment described in the paper. This encompasses the random rooms, quadrant and food versions of the game (you can switch between them by changing the arguments given to the make_env function in the file)
AI Agents Startle Researchers With Unexpected Hide-and-Seek …
Sep 17, 2019 · AI agents construct a fort during a hide-and-seek game developed by OpenAI. Illustration: OpenAI. In OpenAI’s game of hide-and-seek, both the hiders and the seekers received a reward only if they won the game, leaving the …
Clever hide-and-seek AIs learn to use tools and break the rules
Sep 17, 2019 · The latest research from OpenAI put its machine learning agents in a simple game of hide-and-seek, where they pursued an arms race of ingenuity, using objects in unexpected ways to achieve...
- Some results have been removed