Elliot Catt's research while affiliated with Australian National University and other places

Publications (8)

Preprint
Full-text available
Reliable generalization lies at the heart of safe ML and AI. However, understanding when and how neural networks generalize remains one of the most important unsolved problems in the field. In this work, we conduct an extensive empirical study (2200 models, 16 tasks) to investigate whether insights from the theory of computation can predict the lim...
Preprint
Reinforcement Learning formalises an embodied agent's interaction with the environment through observations, rewards and actions. But where do the actions come from? Actions are often considered to represent something external, such as the movement of a limb, a chess piece, or more generally, the output of an actuator. In this work we explore and f...
Article
Reinforcement learners are agents that learn to pick actions that lead to high reward. Ideally, the value of a reinforcement learner’s policy approaches optimality–where the optimal informed policy is the one which maximizes reward. Unfortunately, we show that if an agent is guaranteed to be “asymptotically optimal” in any (stochastically computabl...
Preprint
In this technical report we give an elementary introduction to Quantum Computing for non-physicists. In this introduction we describe in detail some of the foundational Quantum Algorithms including: the Deutsch-Jozsa Algorithm, Shor's Algorithm, Grocer Search, and Quantum Counting Algorithm and briefly the Harrow-Lloyd Algorithm. Additionally we gi...
Conference Paper
Reinforcement Learning agents are expected to eventually perform well. Typically, this takes the form of a guarantee about the asymptotic behavior of an algorithm given some assumptions about the environment. We present an algorithm for a policy whose value approaches the optimal value with probability 1 in all computable probabilistic environments...
Preprint
Reinforcement Learning agents are expected to eventually perform well. Typically, this takes the form of a guarantee about the asymptotic behavior of an algorithm given some assumptions about the environment. We present an algorithm for a policy whose value approaches the optimal value with probability 1 in all computable probabilistic environments...
Conference Paper
The off-switch game is a game theoretic model of a highly intelligent robot interacting with a human. In the original paper by Hadfield-Menell et al. (2016), the analysis is not fully game-theoretic as the human is modelled as an irrational player, and the robot's best action is only calculated under unrealistic normality and soft-max assumptions....

Citations

... As payload is encrypted, it cannot reveal any information. Shannon's [35] and Kolmogorov's [36] entropy values seem promising and can predict some sort of fixed pattern in the payload. Shannon's entropy basically measures the uncertainty of data, whereas Kolmogorov's entropy measures the uncertainty of compressed data. ...
... Kolmogorov complexity has also been considered in the context of reinforcement learning as a tool for complexityconstrained inference [9], [2], [15] based on Solomonoff's theory of inductive inference [19]. We differ by focusing instead on constraining the computational complexity of the obtained policy itself, assuming the underlying system to be known. ...
... Potential control methodologies for superintelligence have been classified into two broad categories, namely capability control and motivational controlbased methods [59]. Capability control methods attempt to limit any harm that the ASI system is able to do by placing it in a restricted environment [38,[60][61][62], adding shut-off mechanisms [63,64], or trip wires [38]. Motivational control methods attempt to design ASI to desire not to cause harm even in the absence of handicapping capability controllers. ...