research
∙
09/05/2023
Explaining grokking through circuit efficiency
One of the most surprising puzzles in neural network generalisation is g...
share
research
∙
02/09/2023
Scaling Goal-based Exploration via Pruning Proto-goals
One of the gnarliest challenges in reinforcement learning (RL) is explor...
research
∙
11/25/2022
Solving math word problems with process- and outcome-based feedback
Recent work has shown that asking language models to generate reasoning ...
research
∙
10/04/2022
Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals
The field of AI alignment is concerned with AI systems that pursue unint...
research
∙
08/17/2022
Discovering Agents
Causal models of agents have been used to analyse the safety aspects of ...
research
∙
01/20/2022
Safe Deep RL in 3D Environments using Human Feedback
Agents should avoid unsafe behaviour during both training and deployment...
research
∙
04/01/2021
Formal Methods for the Informal Engineer: Workshop Recommendations
Formal Methods for the Informal Engineer (FMIE) was a workshop held at t...
research
∙
11/17/2020
Avoiding Tampering Incentives in Deep RL via Decoupled Approval
How can we design agents that pursue a given objective when all feedback...
research
∙
11/17/2020
REALab: An Embedded Perspective on Tampering
This paper describes REALab, a platform for embedded agency research in ...
research
∙
06/20/2019
Modeling AGI Safety Frameworks with Causal Influence Diagrams
Proposals for safe AGI systems are typically made at the level of framew...
research
∙
04/02/2018
Learning to Prove with Tactics
We implement a automated tactical prover TacticToe on top of the HOL4 in...
research
∙
03/09/2018