research
∙
12/28/2022
Lexicographic Multi-Objective Reinforcement Learning
In this work we introduce reinforcement learning techniques for solving ...
share
research
∙
12/06/2022
Misspecification in Inverse Reinforcement Learning
The aim of Inverse Reinforcement Learning (IRL) is to infer a reward fun...
research
∙
09/27/2022
Defining and Characterizing Reward Hacking
We provide the first formal definition of reward hacking, a phenomenon w...
research
∙
03/14/2022
Invariance in Policy Optimisation and Partial Identifiability in Reward Learning
It's challenging to design reward functions for complex, real-world task...
research
∙
01/01/2021
A General Counterexample to Any Decision Theory and Some Responses
In this paper I present an argument and a general schema which can be us...
research
∙
06/26/2020
Is SGD a Bayesian sampler? Well, almost
Overparameterised deep neural networks (DNNs) are highly expressive and ...
research
∙
09/25/2019
Neural networks are a priori biased towards Boolean functions with low entropy
Understanding the inductive bias of neural networks is critical to expla...
research
∙
06/05/2019