Alert button
Picture for Shane Legg

Shane Legg

Alert button

Levels of AGI: Operationalizing Progress on the Path to AGI

Nov 04, 2023
Meredith Ringel Morris, Jascha Sohl-dickstein, Noah Fiedel, Tris Warkentin, Allan Dafoe, Aleksandra Faust, Clement Farabet, Shane Legg

Viaarxiv icon

The Hydra Effect: Emergent Self-repair in Language Model Computations

Jul 28, 2023
Thomas McGrath, Matthew Rahtz, Janos Kramar, Vladimir Mikulik, Shane Legg

Figure 1 for The Hydra Effect: Emergent Self-repair in Language Model Computations
Figure 2 for The Hydra Effect: Emergent Self-repair in Language Model Computations
Figure 3 for The Hydra Effect: Emergent Self-repair in Language Model Computations
Figure 4 for The Hydra Effect: Emergent Self-repair in Language Model Computations
Viaarxiv icon

Randomized Positional Encodings Boost Length Generalization of Transformers

May 26, 2023
Anian Ruoss, Grégoire Delétang, Tim Genewein, Jordi Grau-Moya, Róbert Csordás, Mehdi Bennani, Shane Legg, Joel Veness

Figure 1 for Randomized Positional Encodings Boost Length Generalization of Transformers
Figure 2 for Randomized Positional Encodings Boost Length Generalization of Transformers
Figure 3 for Randomized Positional Encodings Boost Length Generalization of Transformers
Figure 4 for Randomized Positional Encodings Boost Length Generalization of Transformers
Viaarxiv icon

Beyond Bayes-optimality: meta-learning what you know you don't know

Oct 12, 2022
Jordi Grau-Moya, Grégoire Delétang, Markus Kunesch, Tim Genewein, Elliot Catt, Kevin Li, Anian Ruoss, Chris Cundy, Joel Veness, Jane Wang, Marcus Hutter, Christopher Summerfield, Shane Legg, Pedro Ortega

Figure 1 for Beyond Bayes-optimality: meta-learning what you know you don't know
Figure 2 for Beyond Bayes-optimality: meta-learning what you know you don't know
Figure 3 for Beyond Bayes-optimality: meta-learning what you know you don't know
Figure 4 for Beyond Bayes-optimality: meta-learning what you know you don't know
Viaarxiv icon

Neural Networks and the Chomsky Hierarchy

Jul 05, 2022
Grégoire Delétang, Anian Ruoss, Jordi Grau-Moya, Tim Genewein, Li Kevin Wenliang, Elliot Catt, Marcus Hutter, Shane Legg, Pedro A. Ortega

Figure 1 for Neural Networks and the Chomsky Hierarchy
Figure 2 for Neural Networks and the Chomsky Hierarchy
Figure 3 for Neural Networks and the Chomsky Hierarchy
Figure 4 for Neural Networks and the Chomsky Hierarchy
Viaarxiv icon

Your Policy Regularizer is Secretly an Adversary

Apr 01, 2022
Rob Brekelmans, Tim Genewein, Jordi Grau-Moya, Grégoire Delétang, Markus Kunesch, Shane Legg, Pedro Ortega

Figure 1 for Your Policy Regularizer is Secretly an Adversary
Figure 2 for Your Policy Regularizer is Secretly an Adversary
Figure 3 for Your Policy Regularizer is Secretly an Adversary
Figure 4 for Your Policy Regularizer is Secretly an Adversary
Viaarxiv icon

Safe Deep RL in 3D Environments using Human Feedback

Jan 21, 2022
Matthew Rahtz, Vikrant Varma, Ramana Kumar, Zachary Kenton, Shane Legg, Jan Leike

Figure 1 for Safe Deep RL in 3D Environments using Human Feedback
Figure 2 for Safe Deep RL in 3D Environments using Human Feedback
Figure 3 for Safe Deep RL in 3D Environments using Human Feedback
Figure 4 for Safe Deep RL in 3D Environments using Human Feedback
Viaarxiv icon

Model-Free Risk-Sensitive Reinforcement Learning

Nov 04, 2021
Grégoire Delétang, Jordi Grau-Moya, Markus Kunesch, Tim Genewein, Rob Brekelmans, Shane Legg, Pedro A. Ortega

Figure 1 for Model-Free Risk-Sensitive Reinforcement Learning
Figure 2 for Model-Free Risk-Sensitive Reinforcement Learning
Figure 3 for Model-Free Risk-Sensitive Reinforcement Learning
Figure 4 for Model-Free Risk-Sensitive Reinforcement Learning
Viaarxiv icon

Shaking the foundations: delusions in sequence models for interaction and control

Oct 20, 2021
Pedro A. Ortega, Markus Kunesch, Grégoire Delétang, Tim Genewein, Jordi Grau-Moya, Joel Veness, Jonas Buchli, Jonas Degrave, Bilal Piot, Julien Perolat, Tom Everitt, Corentin Tallec, Emilio Parisotto, Tom Erez, Yutian Chen, Scott Reed, Marcus Hutter, Nando de Freitas, Shane Legg

Figure 1 for Shaking the foundations: delusions in sequence models for interaction and control
Figure 2 for Shaking the foundations: delusions in sequence models for interaction and control
Figure 3 for Shaking the foundations: delusions in sequence models for interaction and control
Figure 4 for Shaking the foundations: delusions in sequence models for interaction and control
Viaarxiv icon

Causal Analysis of Agent Behavior for AI Safety

Mar 05, 2021
Grégoire Déletang, Jordi Grau-Moya, Miljan Martic, Tim Genewein, Tom McGrath, Vladimir Mikulik, Markus Kunesch, Shane Legg, Pedro A. Ortega

Figure 1 for Causal Analysis of Agent Behavior for AI Safety
Figure 2 for Causal Analysis of Agent Behavior for AI Safety
Figure 3 for Causal Analysis of Agent Behavior for AI Safety
Figure 4 for Causal Analysis of Agent Behavior for AI Safety
Viaarxiv icon