Tom Everitt

is this you? claim profile

0 followers
Australian National University

Scalable agent alignment via reward modeling: a research direction

One obstacle to applying reinforcement learning algorithms to real-world...
11/19/2018 ∙ by Jan Leike, et al. ∙ 20 ∙ share

read it
The Incentives that Shape Behaviour

Which variables does an agent have an incentive to control with its deci...
01/20/2020 ∙ by Ryan Carey, et al. ∙ 9 ∙ share

read it
Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspective

Can an arbitrarily intelligent reinforcement learning agent be kept unde...
08/13/2019 ∙ by Tom Everitt, et al. ∙ 3 ∙ share

read it
Modeling AGI Safety Frameworks with Causal Influence Diagrams

Proposals for safe AGI systems are typically made at the level of framew...
06/20/2019 ∙ by Tom Everitt, et al. ∙ 2 ∙ share

read it
Count-Based Exploration in Feature Space for Reinforcement Learning

We introduce a new count-based optimistic exploration algorithm for Rein...
06/25/2017 ∙ by Jarryd Martin, et al. ∙ 0 ∙ share

read it
Reinforcement Learning with a Corrupted Reward Channel

No real-world reward function is perfect. Sensory errors and software bu...
05/23/2017 ∙ by Tom Everitt, et al. ∙ 0 ∙ share

read it
A Topological Approach to Meta-heuristics: Analytical Results on the BFS vs. DFS Algorithm Selection Problem

Search is a central problem in artificial intelligence, and BFS and DFS ...
09/09/2015 ∙ by Tom Everitt, et al. ∙ 0 ∙ share

read it
AI Safety Gridworlds

We present a suite of reinforcement learning environments illustrating v...
11/27/2017 ∙ by Jan Leike, et al. ∙ 0 ∙ share

read it
A Game-Theoretic Analysis of the Off-Switch Game

The off-switch game is a game theoretic model of a highly intelligent ro...
08/13/2017 ∙ by Tobias Wängberg, et al. ∙ 0 ∙ share

read it
AGI Safety Literature Review

The development of Artificial General Intelligence (AGI) promises to be ...
05/03/2018 ∙ by Tom Everitt, et al. ∙ 0 ∙ share

read it
Understanding Agent Incentives using Causal Influence Diagrams, Part I: Single Action Settings

Agents are systems that optimize an objective function in an environment...
02/26/2019 ∙ by Tom Everitt, et al. ∙ 0 ∙ share

read it

Tom Everitt

Featured Co-authors

Marcus Hutter

Shane Legg

Pedro A. Ortega

Jan Leike

David Krueger

Laurent Orseau

Miljan Martic

Victoria Krakovna

Ramana Kumar

Ryan Carey

Andrew Lefrancq

Scalable agent alignment via reward modeling: a research direction

The Incentives that Shape Behaviour

Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspective

Modeling AGI Safety Frameworks with Causal Influence Diagrams

Count-Based Exploration in Feature Space for Reinforcement Learning

Reinforcement Learning with a Corrupted Reward Channel

A Topological Approach to Meta-heuristics: Analytical Results on the BFS vs. DFS Algorithm Selection Problem

AI Safety Gridworlds

A Game-Theoretic Analysis of the Off-Switch Game

AGI Safety Literature Review

Understanding Agent Incentives using Causal Influence Diagrams, Part I: Single Action Settings