In many domains, autoregressive models can achieve low log-likelihood on...
Large pre-trained models, also known as foundation models (FMs), are tra...
Particularly in low-data regimes, an outstanding challenge in machine
le...
Meta-training agents with memory has been shown to culminate in Bayes-op...
A structural equation model (SEM) is an effective framework to reason ov...
In many sequential decision-making problems (e.g., robotics control, gam...
As reinforcement learning techniques are increasingly applied to real-wo...
We introduce a new generative model for human planning under the Bayesia...
Recurrent neural networks (RNNs) are widely used to model sequential dat...