Meta Reinforcement Learning with Latent Variable Gaussian Processes
This addresses data efficiency challenges in fields like robotics and drug design by automating task relationship inference, though it is incremental as it builds on existing meta-learning and latent variable methods.
The paper tackles the problem of learning from small datasets in meta reinforcement learning by framing it as a hierarchical latent variable model to automatically infer task relationships from data, resulting in up to a 60% reduction in average interaction time needed to solve tasks compared to baselines.
Learning from small data sets is critical in many practical applications where data collection is time consuming or expensive, e.g., robotics, animal experiments or drug design. Meta learning is one way to increase the data efficiency of learning algorithms by generalizing learned concepts from a set of training tasks to unseen, but related, tasks. Often, this relationship between tasks is hard coded or relies in some other way on human expertise. In this paper, we frame meta learning as a hierarchical latent variable model and infer the relationship between tasks automatically from data. We apply our framework in a model-based reinforcement learning setting and show that our meta-learning model effectively generalizes to novel tasks by identifying how new tasks relate to prior ones from minimal data. This results in up to a 60% reduction in the average interaction time needed to solve tasks compared to strong baselines.