research
∙
07/20/2023
Characterising Decision Theories with Mechanised Causal Graphs
How should my own decisions affect my beliefs about the outcomes I expec...
share
research
∙
05/31/2023
Human Control: Definitions and Algorithms
How can humans stay in control of advanced artificial intelligence syste...
research
∙
01/05/2023
Reasoning about Causality in Games
Causal reasoning and game-theoretic reasoning are fundamental topics in ...
research
∙
08/17/2022
Discovering Agents
Causal models of agents have been used to analyse the safety aspects of ...
research
∙
04/21/2022
Path-Specific Objectives for Safer Agent Incentives
We present a general framework for training safe agents whose naive ince...
research
∙
02/23/2022
A Complete Criterion for Value of Information in Soluble Influence Diagrams
Influence diagrams have recently been used to analyse the safety and fai...
research
∙
02/22/2022
Why Fair Labels Can Yield Unfair Predictions: Graphical Conditions for Introduced Unfairness
In addition to reproducing discriminatory relationships in the training ...
research
∙
10/20/2021
Shaking the foundations: delusions in sequence models for interaction and control
The recent phenomenal success of language models has reinvigorated machi...
research
∙
03/26/2021
Alignment of Language Agents
For artificial intelligence to be beneficial to humans the behaviour of ...
research
∙
02/15/2021
How RL Agents Behave When Their Actions Are Modified
Reinforcement learning in complex environments may require supervision t...
research
∙
02/09/2021
Equilibrium Refinements for Multi-Agent Influence Diagrams: Theory and Practice
Multi-agent influence diagrams (MAIDs) are a popular form of graphical m...
research
∙
02/02/2021
Agent Incentives: A Causal Perspective
We present a framework for analysing agent incentives using causal influ...
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
∙
01/20/2020
The Incentives that Shape Behaviour
Which variables does an agent have an incentive to control with its deci...
research
∙
08/13/2019
Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspective
Can an arbitrarily intelligent reinforcement learning agent be kept unde...
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
∙
02/26/2019
Understanding Agent Incentives using Causal Influence Diagrams, Part I: Single Action Settings
Agents are systems that optimize an objective function in an environment...
research
∙
11/19/2018
Scalable agent alignment via reward modeling: a research direction
One obstacle to applying reinforcement learning algorithms to real-world...
research
∙
05/03/2018
AGI Safety Literature Review
The development of Artificial General Intelligence (AGI) promises to be ...
research
∙
11/27/2017
AI Safety Gridworlds
We present a suite of reinforcement learning environments illustrating v...
research
∙
08/13/2017
A Game-Theoretic Analysis of the Off-Switch Game
The off-switch game is a game theoretic model of a highly intelligent ro...
research
∙
06/25/2017
Count-Based Exploration in Feature Space for Reinforcement Learning
We introduce a new count-based optimistic exploration algorithm for Rein...
research
∙
05/23/2017
Reinforcement Learning with a Corrupted Reward Channel
No real-world reward function is perfect. Sensory errors and software bu...
research
∙
09/09/2015