398 citations · 1.8k across the 163 of their papers we have counts for
6 papers · 1 filter
On the Computability of AIXI
Jan Leike, Marcus Hutter
How could we solve the machine learning and the artificial intelligence problem if we had infinite computation? Solomonoff induction and the reinforcement learning agent AIXI are p…
Bad Universal Priors and Notions of Optimality
Jan Leike, Marcus Hutter
A big open question of algorithmic information theory is the choice of the universal Turing machine (UTM). For Kolmogorov complexity and Solomonoff induction we have invariance the…
A Topological Approach to Meta-heuristics: Analytical Results on the BFS vs. DFS Algorithm Selection Problem
Tom Everitt, Marcus Hutter
Search is a central problem in artificial intelligence, and breadth-first search (BFS) and depth-first search (DFS) are the two most fundamental ways to search. In this paper we de…
On the Computability of Solomonoff Induction and Knowledge-Seeking
Jan Leike, Marcus Hutter
Solomonoff induction is held as a gold standard for learning, but it is known to be incomputable. We quantify its incomputability by placing various flavors of Solomonoff's prior M…
Solomonoff Induction Violates Nicod's Criterion
Jan Leike, Marcus Hutter
Nicod's criterion states that observing a black raven is evidence for the hypothesis H that all ravens are black. We show that Solomonoff induction does not satisfy Nicod's criteri…
Sequential Extensions of Causal and Evidential Decision Theory
Tom Everitt, Jan Leike, Marcus Hutter
Moving beyond the dualistic view in AI where agent and environment are separated incurs new challenges for decision making, as calculation of expected utility is no longer straight…