Search Results for author: Geoffrey Irving

Found 8 papers, 6 papers with code

Alignment of Language Agents

no code implementations26 Mar 2021 Zachary Kenton, Tom Everitt, Laura Weidinger, Iason Gabriel, Vladimir Mikulik, Geoffrey Irving

For artificial intelligence to be beneficial to humans the behaviour of AI agents needs to be aligned with what humans want.

Fine-Tuning Language Models from Human Preferences

3 code implementations18 Sep 2019 Daniel M. Ziegler, Nisan Stiennon, Jeffrey Wu, Tom B. Brown, Alec Radford, Dario Amodei, Paul Christiano, Geoffrey Irving

Most work on reward learning has used simulated environments, but complex information about values is often expressed in natural language, and we believe reward learning for language is a key to making RL practical and safe for real-world tasks.

Language Modelling

AI safety via debate

1 code implementation2 May 2018 Geoffrey Irving, Paul Christiano, Dario Amodei

To make AI systems broadly useful for challenging real-world tasks, we need them to learn complex human goals and preferences.

Deep Network Guided Proof Search

no code implementations24 Jan 2017 Sarah Loos, Geoffrey Irving, Christian Szegedy, Cezary Kaliszyk

Here we suggest deep learning based guidance in the proof search of the theorem prover E. We train and compare several deep neural network models on the traces of existing ATP proofs of Mizar statements and use them to select processed clauses during proof search.

Game of Go Image Captioning +4

DeepMath - Deep Sequence Models for Premise Selection

2 code implementations NeurIPS 2016 Alex A. Alemi, Francois Chollet, Niklas Een, Geoffrey Irving, Christian Szegedy, Josef Urban

We study the effectiveness of neural sequence models for premise selection in automated theorem proving, one of the main bottlenecks in the formalization of mathematics.

Automated Theorem Proving

Cannot find the paper you are looking for? You can Submit a new open access paper.