Scaling Laws for Pre-training Agents and World Models

Understand

The performance of embodied agents has been shown to improve by increasing model parameters, dataset size, and compute.

• This has been demonstrated in domains from robotics to video games, when generative learning objectives on offline datasets (pre-training) are used to model an agent's behavior (imitation learning) or their environment (world modeling).
• This paper characterizes the role of scale in these tasks more precisely.
• Going beyond the simple intuition that `bigger is better', we show that the same types of power laws found in language modeling also arise in world modeling and imitation learning (e.g.