Haitham Bou AmmarFeb 18, 201912 min readReinforcement Learning as Probabilistic Modelling: A Variational Inference Formulation (Part II) WIPHaving introduced the variational inference formulation of dynamical systems, now we are ready to formulate reinforcement learning as a...
Haitham Bou AmmarFeb 14, 201915 min readReinforcement Learning as Probabilistic Modelling: A Variational Inference Formulation (Part I) WIPReinforcement Learning is concerned with an agent attempting to acquire optimal behaviour in unknown environments that typically exhibit...
Haitham Bou AmmarFeb 13, 20194 min readGoogle Co-Lab and PyTorchRecent advances in machine learning, especially those in deep learning, have been enabled by innovations in computer hardware that...