The diversity and dynamism of the real world require reinforcement learning (RL) agents that can quickly adapt and learn new behaviors when placed in novel situations.

Vision-and-Language Navigation requires the agent to follow language instructions to navigate through 3D environments.

In this section, we present the training algorithm for Self-Tuning Networks. The full algorithm is showninAlg.2.

For each prediction task, we select features that have a causal influence on the target of prediction.

In ICL, a conditional generative model (CGM) is prompted with a dataset and a prediction question and asked to generate a response.

The task is to i) predict the unknown parameters, then ii) solve the optimization problem using the predicted parameters, such that the resulting solutions are good even under true parameters.