180 citations
- Massachusetts Institute of TechnologyUS38 papers
- University of BonnDE37 papers
- University of OxfordGB36 papers
- Centre National de la Recherche ScientifiqueFR35 papers
- Centro Brasileiro de Pesquisas FísicasBR35 papers
- École Polytechnique Fédérale de LausanneCH35 papers
- Lamarr Institute for Machine Learning and Artificial Intelligence35 papers
- Ruhr University BochumDE35 papers
- Sorbonne UniversitéFR35 papers
- University of BolognaIT35 papers
- University of CambridgeGB35 papers
- University of SienaIT35 papers
8 papers · 1 filter
Corrigibility as a Singular Target: A Vision for Inherently Reliable Foundation Models
Ram Potham, Max Harms
Foundation models (FMs) face a critical safety challenge: as capabilities scale, instrumental convergence drives default trajectories toward loss of human control, potentially culm…
A Theory of Bounded Inductive Rationality
Caspar Oesterheld, Abram Demski, Vincent Conitzer
The dominant theories of rational choice assume logical omniscience. That is, they assume that when facing a decision problem, an agent can perform all relevant computations and de…
Graph-guided random forest for gene set selection
Bastian Pfeifer, Hubert Baniecki, Anna Saranti +2
Machine learning methods can detect complex relationships between variables, but usually do not exploit domain knowledge. This is a limitation because in many scientific discipline…
Recent Advances in Neural Program Synthesis
Neel Kant
In recent years, deep learning has made tremendous progress in a number of fields that were previously out of reach for artificial intelligence. The successes in these problems has…
Occam's razor is insufficient to infer the preferences of irrational agents
Stuart Armstrong, Sören Mindermann
Inverse reinforcement learning (IRL) attempts to infer human rewards or preferences from observed behavior. Since human planning systematically deviates from rationality, several a…
Toward negotiable reinforcement learning: shifting priorities in Pareto optimal sequential decision-making
Andrew Critch
Existing multi-objective reinforcement learning (MORL) algorithms do not account for objectives that arise from players with differing beliefs. Concretely, consider two players wit…