1 code implementation • 4 Oct 2022 • Michael K. Cohen, Samuel Daulton, Michael A. Osborne
We present a new kernel that allows for Gaussian process regression in $O((n+m)\log(n+m))$ time.
no code implementations • 13 May 2021 • Michael K. Cohen, Badri Vellambi, Marcus Hutter
Algorithmic Information Theory has inspired intractable constructions of general intelligence (AGI), and undiscovered tractable approximations are likely feasible.
no code implementations • 17 Feb 2021 • Michael K. Cohen, Marcus Hutter, Neel Nanda
If we run an imitator, we probably want events to unfold similarly to the way they would have if the demonstrator had been acting the whole time.
no code implementations • 15 Jun 2020 • Michael K. Cohen, Marcus Hutter
Our other main contribution is that the agent's policy's value approaches at least that of the mentor, while the probability of deferring to the mentor goes to 0.
1 code implementation • 5 Jun 2020 • Michael K. Cohen, Elliot Catt, Marcus Hutter
Much work in reinforcement learning uses an ergodicity assumption to avoid this problem.
no code implementations • 29 May 2019 • Michael K. Cohen, Badri Vellambi, Marcus Hutter
General intelligence, the ability to solve arbitrary solvable problems, is supposed by many to be artificially constructible.
no code implementations • 4 Mar 2019 • Michael K. Cohen, Elliot Catt, Marcus Hutter
This is known as strong asymptotic optimality, and it was previously unknown whether it was possible for a policy to be strongly asymptotically optimal in the class of all computable probabilistic environments.