- Generalised Discount Functions applied to a Monte-Carlo AIμ Implementation. (Lamont, S., Aslanides, J., Leike, J., Hutter, M. (2017). arXiv preprint arXiv:103.01358v1)
- Universal Reinforcement Learning Algorithms: Survey and Experiments. (Aslanides, J., Leike, J., Hutter, M. (2017). arXiv:1705.10557v1)
- Exploration potential. (Leike, J. 2016. arXiv preprint: arXiv:1609.04994)
- Thompson sampling is asymptotically optimal in general environments. (Leike, J., Lattimore, T., Orseau, L. & Hutter, M. (2016). Proceedings of the Thirty-Second Uncertainty in Artificial Intelligence Conference)
- A formal solution to the grain of truth problem. Proceedings of the Thirty-Second Uncertainty in Artificial Intelligence Conference. (Leike, J., Taylor, J., Fallenstein, B. (2016).)