Knowledge Infused Policy Gradients for Adaptive Pandemic Control

Abstract

COVID-19 has impacted nations differently based on their policy implementations. The effective policy requires taking into account public information and adaptability to new knowledge. Epidemiological models built to understand COVID-19 seldom provide the policymaker with the capability for adaptive pandemic control (APC). Among the core challenges to be overcome include (a) inability to handle a high degree of non-homogeneity in different contributing features across the pandemic timeline, (b) lack of an approach that enables adaptive incorporation of public health expert knowledge, and (c) transparent models that enable understanding of the decision-making process in suggesting policy. In this work, we take the early steps to address these challenges using Knowledge Infused Policy Gradient (KIPG) methods. Prior work on knowledge infusion does not handle soft and hard imposition of varying forms of knowledge in disease information and guidelines to necessarily comply with. Furthermore, the models do not attend to non-homogeneity in feature counts, manifesting as partial observability in informing the policy. Additionally, interpretable structures are extracted post-learning instead of learning an interpretable model required for APC. To this end, we introduce a mathematical framework for KIPG methods that can (a) induce relevant feature counts over multi-relational features of the world, (b) handle latent non-homogeneous counts as hidden variables that are linear combinations of kernelized aggregates over the features, and (b) infuse knowledge as functional constraints in a principled manner. The study establishes a theory for imposing hard and soft constraints and simulates it through experiments. In comparison with knowledge-intensive baselines, we show quick sample efficient adaptation to new knowledge and interpretability in the learned policy, especially in a pandemic context.

Knowledge Infused Policy Gradients with Upper Confidence Bound for Relational Bandits

“…Thus, we observe that we can instead directly optimize for the optimal arm choice through policy gradient methods [6]. Using a Bayesian formulation for optimization of policy in functional space, we can see that the knowledge infused reshape function can be automatically learned by an adaption of the Knowledge Infused Policy Gradients (KIPG) algorithm for the Reinforcement Learning (RL) setting to the CB setting [7], which takes as input a state and knowledge, and outputs an action.…”