Paul Francis Christiano
According to our database1, Paul Francis Christiano authored at least 13 papers between 2014 and 2018.
Legend:Book In proceedings Article PhD thesis Other
Supervising strong learners by amplifying weak experts.
Unrestricted Adversarial Examples.
AI safety via debate.
Manipulation-resistant online learning.
PhD thesis, 2017
Deep reinforcement learning from human preferences.
Deep Reinforcement Learning from Human Preferences.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017
A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models.
Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Model.
Concrete Problems in AI Safety.
Theano: A Python framework for fast computation of mathematical expressions.
Reflective Oracles: A Foundation for Classical Game Theory.
Reflective Oracles: A Foundation for Game Theory in Artificial Intelligence.
Proceedings of the Logic, Rationality, and Interaction - 5th International Workshop, 2015
Robust Cooperation in the Prisoner's Dilemma: Program Equilibrium via Provability Logic.