1 code implementation • 17 Jul 2017 • William Saunders, Girish Sastry, Andreas Stuhlmueller, Owain Evans
We formalize human intervention for RL and show how to reduce the human labor required by training a supervised learner to imitate the human's intervention decisions.
no code implementations • 18 Dec 2015 • Owain Evans, Andreas Stuhlmueller, Noah D. Goodman
If we assume that choices are approximately optimal according to some utility function, we can treat preference inference as Bayesian inverse planning.
no code implementations • NeurIPS 2011 • David Wingate, Noah Goodman, Andreas Stuhlmueller, Jeffrey M. Siskind
Probabilistic programming languages allow modelers to specify a stochastic process using syntax that resembles modern programming languages.