The expressivity of current deep probabilistic models can be improved by selectively prioritizing statistical dependencies between latent variables that are potentially distant from each other.
In this blog post, we aim to understand if, when and why offline RL is a better approach for tackling a variety of sequential decision-making problems.
Unsupervised reinforcement learning (RL), where RL agents pre-train with self-supervised rewards, is an emerging paradigm for developing RL agents that are capable of generalization.
imodels provides a simple unified interface and implementation for many state-of-the-art interpretable modeling techniques, particularly rule-based methods.
With our proposed dataset and multi-task, multi-domain learning approach, we have shown one potential avenue for making diverse datasets reusable in robotics.