Goal-based wealth management with generative reinforcement learning

A combination of machine learning techniques provides multi-period portfolio optimisation

CLICK HERE TO DOWNLOAD THE PDF

Matthew Dixon and Igor Halperin develop a reinforcement learning (RL) approach to goal-based wealth management problems such as optimisation of retirement plans or target date funds. They present G-Learner: a reinforcement learning algorithm that does not assume a data generation process and is suitable for noisy data. Their approach is based on G-learning, a probabilistic extension of the Q-learning method of reinforcement learning. In addition to G-Learners