TradeWindow, led by AJ Smith, an experienced innovator and investor in rapid-growth companies, offers digital solutions designed to deliver increased value and transparency to exporters, importers, freight forwarders and customs brokers to maximise productivity and minimise cost. Their digital trade platform enables organisations in global trade to securely exchange data across the supply chain ecosystem, while seamlessly integrating into their back-end operations. TradeWindow's solutions allow information sharing and collaboration with global supply chain stakeholders to provide instantaneous access through their enterprise-grade platform. With TradeWindow, users can access an immutable record of activity created in the platform. This single source of data improves visibility across customers, ports, terminals, shipping lines, banks, insurance companies and government authorities.

Bayesian reinforcement learning (BRL) offers a decision-theoretic solution to the problem of reinforcement learning. However, typical model-based BRL algorithms have focused either on ma intaining a posterior distribution on models or value functions and combining this with approx imate dynamic programming or tree search. This paper describes a novel backwards induction pri nciple for performing joint Bayesian estimation of models and value functions, from which many new BRL algorithms can be obtained. We demonstrate this idea with algorithms and experiments in discrete state spaces.