Here’s a link towards DreamerV3, a new model from DeepMind that can be trained on a bunch of different tasks (including a simplified version of Minecraft) and outperform more narrow models. Link: https://arxiv.org/pdf/2301.04104v1.pdf
The most surprising bits are that:
The type of tasks they train it on is fairly diverse
Data efficiency scales with the number of parameters
They so far haven’t scaled it that far and got pretty good results
[Linkpost] DreamerV3: A General RL Architecture
Link post
Here’s a link towards DreamerV3, a new model from DeepMind that can be trained on a bunch of different tasks (including a simplified version of Minecraft) and outperform more narrow models. Link: https://arxiv.org/pdf/2301.04104v1.pdf
The most surprising bits are that:
The type of tasks they train it on is fairly diverse
Data efficiency scales with the number of parameters
They so far haven’t scaled it that far and got pretty good results