I am using this GitBook to document my own ideas and knowledge in real time. I will cite source papers as much as possible, but if I don't cite something and you want a source, contact me. I take no responsibility for the correctness or completeness of the information presented in these pages.
That said, if you want to build on some of my original ideas or proposals in your own research publications, please do! Cite this book as you would any other online resource or eBook.
I am an Artificial Intelligence researcher from Australia. Until recently I worked with Marcus Hutter at the Australian National University, Canberra. Broadly I'm interested in reinforcement learning (RL), AI Safety, generative modelling, and natural language understanding. My past research has focused on intrinsic motivation approaches to the exploration problem in RL, and on the control problem in AI Safety. Prior to working on AI, I completed my honours research on the philosophy of language under Andrew Inkpin at the University of Melbourne. I focused on Merleau-Ponty's account of linguistic meaning. I have also worked on computational neuroscience with groups at the University of Melbourne and the University of Sydney.
See my homepage for a list of my research publications: https://jarrydmartin.com