Multi-Agent Hide and Seek
Channel:OpenAI · Length:2:57 · Published:2019-09-17 · Views:11308615
Summary
OpenAI's short demo of agents playing hide-and-seek in a simulated environment. Through self-play, the agents develop six progressively more complex strategies and counter-strategies, including tool use.
Why HN recommends it
HN uses it as a vivid example of emergent behavior from multi-agent reinforcement learning, and as a way to make AI misalignment concerns feel concrete.
This short video makes the concern much more real — HN, 2019
Machine learning & deep learning · AI safety, AGI & impact
Subtitles (excerpt)
on earth the simple rules of natural selection and competition led to the evolution of increasingly intelligent life-forms today we ask if comparably simple rules at multi-agent competition can also lead to intelligent behavior in a new virtual world these agents are playing hide and seek these agents have just begun learning but they've already learned to chase and run away this is a hard world for a hider who has only learned to flee however after training and millions of rounds of hide-and-seek the hiders find a solution the hiders learn to use rudimentary tools to their advantage by grabbing and locking these blocks they can create their own shelter the Seekers are locked in place for a brief period at the start of the game giving hiders a chance to prepare even so the hiders must learn to collaborate accomplishing tasks that would be impossible for any single individual the hiders are not the only ones who can learn to use tools after many generations of failing to break into the shelter the Seekers learned to jump over obstacles using ramps however after many millions of rounds of having their shelter breached the hiders learned to take away the primary tool the Seekers have at their disposal note that
On Hacker News
Specialized AI is unlikely to be a threat. The issue will be with general AI, and simple but not fully thought out utility functions. This short video makes the concern much more real: [VIDEO] Consider what would happen if you took that same AI, make its utility function similar to this: [LINK] , and released it on the internet. — aeternum, 2019-10
True RL is not limited by being tethered to human-annotated data, and it is able to create novel approaches to solve problems. True RL requires a very clear objective function (such as the rules of Go, or Starcraft, or Taboo!) that the model can evaluate itself against. Andrej Karpathy talks about the difference between RLHF and "true" RL here: [LINK] > The other thing is that we're doing reinfor… — HanClinto, 2024-07
Here [1]. They called it "emergent" property, but I only see that as inevitable behaviour. [1] [VIDEO] — PartiallyTyped, 2022-09
> There's just something I can't describe with words about what it lacks today - where it's possibly more philosophical than technical My personal viewpoint is that there's nothing inherently special about biological intelligence that can't theoretically be reproduced with electronics, but that today's AI has some practical limitations like no significant persistent internal state. I saw an "Inne… — treesprite82, 2022-07
I think evolution is not an undirected process in that sense because it's an optimization process, that optimizes to create more copies of itself. Superintelligence will likely use some Evolutionary Computation (see en.wikipedia.org/wiki/Evolutionary_computation ). Also see Karl Sims 'Creatures' from the 90s: youtube.com/watch?v=JBgG_VSP7f8 or OpenAI's Multi-Agent Hide and Seek: [VIDEO] — HaukeHi, 2022-03
Related videos
- Richard Feynman on Pseudoscience · Jacob Edward · 1:53
- Tesla AI Day 2022 · Tesla · 3:23:00
- The spelled-out intro to neural networks and backpropagation: building micrograd · Andrej Karpathy · 2:25:52
- But what is a neural network? | Deep learning chapter 1 · 3Blue1Brown · 18:40
- What Happened to Horses Is Happening to Us · CGP Grey · 15:00
- AlphaGo - The Movie | Full award-winning documentary · Google DeepMind · 1:30:28
- Transformers, the tech behind LLMs | Deep Learning Chapter 5 · 3Blue1Brown · 27:14
- USENIX Security '18-Q: Why Do Keynote Speakers Keep Suggesting That Improving Security Is Possible? · USENIX · 51:22
- Lecture 1 | Machine Learning (Stanford) · Stanford · 1:08:40
- MarI/O - Machine Learning for Video Games · SethBling · 5:57
- Deep Dive into LLMs like ChatGPT · Andrej Karpathy · 3:31:23
- Computer program that learns to play classic NES games · suckerpinch · 16:17
- RL Course by David Silver - Lecture 1: Introduction to Reinforcement Learning · Google DeepMind · 1:28:12
- Let's build GPT: from scratch, in code, spelled out. · Andrej Karpathy · 1:56:20
- Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learning · Google TechTalks · 48:10
- A Hackers' Guide to Language Models · Jeremy Howard · 1:31:13