My favourite past projects have included:

- Developing a unified method for promoting cooperation and communication among in multi-agent reinforcement learning (RL) by creating an intrinsic reward based on assessing causal influence between agents.

- Improving deep generative models by using human facial expression responses to samples from the model as a training signal.

- Effectively combining supervised learning and RL to train generative sequence models.

- Using multi-task learning techniques to personalize machine learning models and improve accuracy in predicting next day stress, happiness and health.