#ai Created at 2023-01-13 # [Anonymous feedback](https://www.admonymous.co/louis030195) # [[Epistemic status]] #shower-thought Last modified date: 2023-01-13 Commit: 0 # Related - [[Computing/Memory palaces]] - [[Computing/Intelligence/Can machine think creatively]] # TODO > [!TODO] TODO # AI in artificial reality List of advances in using [[Artificial intelligence|AI]] to solve [[Artificial reality|artificial reality]] problems with the same inputs than humans. (i.e. pixel screen, keyboard, etc.) ## Minecraft >General intelligence requires solving tasks across many domains. Current reinforcement learning algorithms carry this potential but are held back by the resources and knowledge required to tune them for new tasks. We present DreamerV3, a general and scalable algorithm based on world models that outperforms previous approaches across a wide range of domains with fixed hyperparameters. These domains include continuous and discrete actions, visual and low-dimensional inputs, 2D and 3D worlds, different data budgets, reward frequencies, and reward scales. We observe favorable scaling properties of DreamerV3, with larger models directly translating to higher data-efficiency and final performance. Applied out of the box, DreamerV3 is the first algorithm to collect diamonds in Minecraft from scratch without human data or curricula, a long-standing challenge in artificial intelligence. Our general algorithm makes reinforcement learning broadly applicable and allows scaling to hard decision making problems.[^1] DreamerV3 is a special computer program that helps computers make better decisions. It can figure out how to do things in different ways and works in lots of different situations. It can learn how to do things in 2D and 3D worlds, with different types of data and rewards, and even in a game like Minecraft. It's really good at this and can do things that other computer programs can't do. [^1]: https://arxiv.org/pdf/2301.04104v1.pdf