Causal Analysis of Agent Behavior for AI Safety

no code implementations • 5 Mar 2021 • Grégoire Déletang, Jordi Grau-Moya, Miljan Martic, Tim Genewein, Tom McGrath, Vladimir Mikulik, Markus Kunesch, Shane Legg, Pedro A. Ortega

As machine learning systems become more powerful they also become increasingly unpredictable and opaque.

Algorithms for Causal Reasoning in Probability Trees

2 code implementations • 23 Oct 2020 • Tim Genewein, Tom McGrath, Grégoire Déletang, Vladimir Mikulik, Miljan Martic, Shane Legg, Pedro A. Ortega

Probability trees are one of the simplest models of causal generative processes.

Meta-trained agents implement Bayes-optimal agents

no code implementations • NeurIPS 2020 • Vladimir Mikulik, Grégoire Delétang, Tom McGrath, Tim Genewein, Miljan Martic, Shane Legg, Pedro A. Ortega

Memory-based meta-learning is a powerful technique to build agents that adapt fast to any task within a target distribution.

Meta-Learning

Meta-learning of Sequential Strategies

no code implementations • 8 May 2019 • Pedro A. Ortega, Jane. X. Wang, Mark Rowland, Tim Genewein, Zeb Kurth-Nelson, Razvan Pascanu, Nicolas Heess, Joel Veness, Alex Pritzel, Pablo Sprechmann, Siddhant M. Jayakumar, Tom McGrath, Kevin Miller, Mohammad Azar, Ian Osband, Neil Rabinowitz, András György, Silvia Chiappa, Simon Osindero, Yee Whye Teh, Hado van Hasselt, Nando de Freitas, Matthew Botvinick, Shane Legg

In this report we review memory-based meta-learning as a tool for building sample-efficient strategies that learn from past experience to adapt to any task within a target class.

Meta-Learning