research
∙
05/29/2023
Doing the right thing for the right reason: Evaluating artificial moral cognition by probing cost insensitivity
Is it possible to evaluate the moral cognition of complex artificial age...
share
research
∙
09/30/2022
Beyond Bayes-optimality: meta-learning what you know you don't know
Meta-training agents with memory has been shown to culminate in Bayes-op...
research
∙
03/23/2022
Your Policy Regularizer is Secretly an Adversary
Policy regularization methods such as maximum entropy regularization are...
research
∙
11/04/2021
Model-Free Risk-Sensitive Reinforcement Learning
We extend temporal-difference (TD) learning in order to obtain risk-sens...
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
∙
03/05/2021
Causal Analysis of Agent Behavior for AI Safety
As machine learning systems become more powerful they also become increa...
research
∙
10/14/2020