no code implementations • 13 Mar 2024 • SIMA Team, Maria Abi Raad, Arun Ahuja, Catarina Barros, Frederic Besse, Andrew Bolt, Adrian Bolton, Bethanie Brownfield, Gavin Buttimore, Max Cant, Sarah Chakera, Stephanie C. Y. Chan, Jeff Clune, Adrian Collister, Vikki Copeman, Alex Cullum, Ishita Dasgupta, Dario de Cesare, Julia Di Trapani, Yani Donchev, Emma Dunleavy, Martin Engelcke, Ryan Faulkner, Frankie Garcia, Charles Gbadamosi, Zhitao Gong, Lucy Gonzales, Kshitij Gupta, Karol Gregor, Arne Olav Hallingstad, Tim Harley, Sam Haves, Felix Hill, Ed Hirst, Drew A. Hudson, Jony Hudson, Steph Hughes-Fitt, Danilo J. Rezende, Mimi Jasarevic, Laura Kampis, Rosemary Ke, Thomas Keck, Junkyung Kim, Oscar Knagg, Kavya Kopparapu, Rory Lawton, Andrew Lampinen, Shane Legg, Alexander Lerchner, Marjorie Limont, YuLan Liu, Maria Loks-Thompson, Joseph Marino, Kathryn Martin Cussons, Loic Matthey, Siobhan Mcloughlin, Piermaria Mendolicchio, Hamza Merzic, Anna Mitenkova, Alexandre Moufarek, Valeria Oliveira, Yanko Oliveira, Hannah Openshaw, Renke Pan, Aneesh Pappu, Alex Platonov, Ollie Purkiss, David Reichert, John Reid, Pierre Harvey Richemond, Tyson Roberts, Giles Ruscoe, Jaume Sanchez Elias, Tasha Sandars, Daniel P. Sawyer, Tim Scholtes, Guy Simmons, Daniel Slater, Hubert Soyer, Heiko Strathmann, Peter Stys, Allison C. Tam, Denis Teplyashin, Tayfun Terzi, Davide Vercelli, Bojan Vujatovic, Marcus Wainwright, Jane X. Wang, Zhengdong Wang, Daan Wierstra, Duncan Williams, Nathaniel Wong, Sarah York, Nick Young
Building embodied AI systems that can follow arbitrary language instructions in any 3D environment is a key challenge for creating general AI.
no code implementations • 4 Nov 2023 • Meredith Ringel Morris, Jascha Sohl-Dickstein, Noah Fiedel, Tris Warkentin, Allan Dafoe, Aleksandra Faust, Clement Farabet, Shane Legg
We propose a framework for classifying the capabilities and behavior of Artificial General Intelligence (AGI) models and their precursors.
no code implementations • 28 Jul 2023 • Thomas McGrath, Matthew Rahtz, Janos Kramar, Vladimir Mikulik, Shane Legg
We investigate the internal structure of language model computations using causal analysis and demonstrate two motifs: (1) a form of adaptive computation where ablations of one attention layer of a language model cause another layer to compensate (which we term the Hydra effect) and (2) a counterbalancing function of late MLP layers that act to downregulate the maximum-likelihood token.
1 code implementation • 26 May 2023 • Anian Ruoss, Grégoire Delétang, Tim Genewein, Jordi Grau-Moya, Róbert Csordás, Mehdi Bennani, Shane Legg, Joel Veness
Transformers have impressive generalization capabilities on tasks with a fixed context length.
no code implementations • 30 Sep 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
This is in contrast to risk-sensitive agents, which additionally exploit the higher-order moments of the return, and ambiguity-sensitive agents, which act differently when recognizing situations in which they lack knowledge.
2 code implementations • 5 Jul 2022 • Grégoire Delétang, Anian Ruoss, Jordi Grau-Moya, Tim Genewein, Li Kevin Wenliang, Elliot Catt, Chris Cundy, Marcus Hutter, Shane Legg, Joel Veness, Pedro A. Ortega
Reliable generalization lies at the heart of safe ML and AI.
no code implementations • 23 Mar 2022 • Rob Brekelmans, Tim Genewein, Jordi Grau-Moya, Grégoire Delétang, Markus Kunesch, Shane Legg, Pedro Ortega
Policy regularization methods such as maximum entropy regularization are widely used in reinforcement learning to improve the robustness of a learned policy.
no code implementations • 20 Jan 2022 • Matthew Rahtz, Vikrant Varma, Ramana Kumar, Zachary Kenton, Shane Legg, Jan Leike
In this paper we answer this question in the affirmative, using ReQueST to train an agent to perform a 3D first-person object collection task using data entirely from human contractors.
no code implementations • 4 Nov 2021 • Grégoire Delétang, Jordi Grau-Moya, Markus Kunesch, Tim Genewein, Rob Brekelmans, Shane Legg, Pedro A. Ortega
Since the Gaussian free energy is known to be a certainty-equivalent sensitive to the mean and the variance, the learning rule has applications in risk-sensitive decision-making.
no code implementations • 20 Oct 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
The recent phenomenal success of language models has reinvigorated machine learning research, and large sequence models such as transformers are being applied to a variety of domains.
no code implementations • NeurIPS 2021 • Grégoire Delétang, Jordi Grau-Moya, Markus Kunesch, Tim Genewein, Rob Brekelmans, Shane Legg, Pedro A Ortega
Since the Gaussian free energy is known to be a certainty-equivalent sensitive to the mean and the variance, the learning rule has applications in risk-sensitive decision-making.
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.
no code implementations • 2 Feb 2021 • Tom Everitt, Ryan Carey, Eric Langlois, Pedro A Ortega, Shane Legg
We propose a new graphical criterion for value of control, establishing its soundness and completeness.
no code implementations • 17 Nov 2020 • Ramana Kumar, Jonathan Uesato, Richard Ngo, Tom Everitt, Victoria Krakovna, Shane Legg
Standard Markov Decision Process (MDP) formulations of RL and simulated environments mirroring the MDP structure assume secure access to feedback (e. g., rewards).
no code implementations • 17 Nov 2020 • Jonathan Uesato, Ramana Kumar, Victoria Krakovna, Tom Everitt, Richard Ngo, Shane Legg
How can we design agents that pursue a given objective when all feedback mechanisms are influenceable by the agent?
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.
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.
no code implementations • NeurIPS 2020 • Victoria Krakovna, Laurent Orseau, Richard Ngo, Miljan Martic, Shane Legg
To avoid this interference incentive, we introduce a baseline policy that represents a default course of action (such as doing nothing), and use it to filter out future tasks that are not achievable by default.
1 code implementation • ICLR 2021 • Adam Gleave, Michael Dennis, Shane Legg, Stuart Russell, Jan Leike
However, this method cannot distinguish between the learned reward function failing to reflect user preferences and the policy optimization process failing to optimize the learned reward.
no code implementations • 28 Apr 2020 • Stuart Armstrong, Jan Leike, Laurent Orseau, Shane Legg
We formally introduce two desirable properties: the first is `unriggability', which prevents the agent from steering the learning process in the direction of a reward function that is easier to optimise.
no code implementations • 20 Jan 2020 • Ryan Carey, Eric Langlois, Tom Everitt, Shane Legg
Which variables does an agent have an incentive to control with its decision, and which variables does it have an incentive to respond to?
1 code implementation • ICML 2020 • Siddharth Reddy, Anca D. Dragan, Sergey Levine, Shane Legg, Jan Leike
To address this challenge, we propose an algorithm that safely and interactively learns a model of the user's reward function.
no code implementations • 25 Sep 2019 • David Scott Krueger, Tegan Maharaj, Shane Legg, Jan Leike
Decisions made by machine learning systems have increasing influence on the world.
no code implementations • 20 Jun 2019 • Tom Everitt, Ramana Kumar, Victoria Krakovna, Shane Legg
Proposals for safe AGI systems are typically made at the level of frameworks, specifying how the components of the proposed system should be trained and interact with each other.
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.
no code implementations • 26 Feb 2019 • Tom Everitt, Pedro A. Ortega, Elizabeth Barnes, Shane Legg
Modeling the agent-environment interaction using causal influence diagrams, we can answer two fundamental questions about an agent's incentives directly from the graph: (1) which nodes can the agent have an incentivize to observe, and (2) which nodes can the agent have an incentivize to control?
no code implementations • 8 Jan 2019 • Laurent Orseau, Tor Lattimore, Shane Legg
We consider prediction with expert advice under the log-loss with the goal of deriving efficient and robust algorithms.
no code implementations • ICLR 2019 • Miljan Martic, Jan Leike, Andrew Trask, Matteo Hessel, Shane Legg, Pushmeet Kohli
Currently the only techniques for sharing governance of a deep learning model are homomorphic encryption and secure multiparty computation.
3 code implementations • 19 Nov 2018 • Jan Leike, David Krueger, Tom Everitt, Miljan Martic, Vishal Maini, Shane Legg
One obstacle to applying reinforcement learning algorithms to real-world problems is the lack of suitable reward functions.
2 code implementations • NeurIPS 2018 • Borja Ibarz, Jan Leike, Tobias Pohlen, Geoffrey Irving, Shane Legg, Dario Amodei
To solve complex real-world problems with reinforcement learning, we cannot rely on manually specified reward functions.
no code implementations • 30 Jun 2018 • Pedro A. Ortega, Shane Legg
How can one detect friendly and adversarial behavior from raw data?
no code implementations • 4 Jun 2018 • Victoria Krakovna, Laurent Orseau, Ramana Kumar, Miljan Martic, Shane Legg
How can we design safe reinforcement learning agents that avoid unnecessary disruptions to their environment?
no code implementations • 31 May 2018 • Laurent Orseau, Simon McGregor McGill, Shane Legg
According to Dennett, the same system may be described using a `physical' (mechanical) explanatory stance, or using an `intentional' (belief- and goal-based) explanatory stance.
24 code implementations • ICML 2018 • Lasse Espeholt, Hubert Soyer, Remi Munos, Karen Simonyan, Volodymir Mnih, Tom Ward, Yotam Doron, Vlad Firoiu, Tim Harley, Iain Dunning, Shane Legg, Koray Kavukcuoglu
In this work we aim to solve a large collection of tasks using a single reinforcement learning agent with a single set of parameters.
Ranked #3 on
Atari Games
on Atari 2600 Skiing
(using extra training data)
1 code implementation • 24 Jan 2018 • Joel Z. Leibo, Cyprien de Masson d'Autume, Daniel Zoran, David Amos, Charles Beattie, Keith Anderson, Antonio García Castañeda, Manuel Sanchez, Simon Green, Audrunas Gruslys, Shane Legg, Demis Hassabis, Matthew M. Botvinick
Psychlab is a simulated psychology laboratory inside the first-person 3D game world of DeepMind Lab (Beattie et al. 2016).
2 code implementations • 27 Nov 2017 • Jan Leike, Miljan Martic, Victoria Krakovna, Pedro A. Ortega, Tom Everitt, Andrew Lefrancq, Laurent Orseau, Shane Legg
We present a suite of reinforcement learning environments illustrating various safety properties of intelligent agents.
15 code implementations • ICLR 2018 • Meire Fortunato, Mohammad Gheshlaghi Azar, Bilal Piot, Jacob Menick, Ian Osband, Alex Graves, Vlad Mnih, Remi Munos, Demis Hassabis, Olivier Pietquin, Charles Blundell, Shane Legg
We introduce NoisyNet, a deep reinforcement learning agent with parametric noise added to its weights, and show that the induced stochasticity of the agent's policy can be used to aid efficient exploration.
Ranked #1 on
Atari Games
on Atari 2600 Surround
6 code implementations • NeurIPS 2017 • Paul Christiano, Jan Leike, Tom B. Brown, Miljan Martic, Shane Legg, Dario Amodei
For sophisticated reinforcement learning (RL) systems to interact usefully with real-world environments, we need to communicate complex goals to these systems.
1 code implementation • 23 May 2017 • Tom Everitt, Victoria Krakovna, Laurent Orseau, Marcus Hutter, Shane Legg
Traditional RL methods fare poorly in CRMDPs, even under strong simplifying assumptions and when trying to compensate for the possibly corrupt rewards.
5 code implementations • 12 Dec 2016 • Charles Beattie, Joel Z. Leibo, Denis Teplyashin, Tom Ward, Marcus Wainwright, Heinrich Küttler, Andrew Lefrancq, Simon Green, Víctor Valdés, Amir Sadik, Julian Schrittwieser, Keith Anderson, Sarah York, Max Cant, Adam Cain, Adrian Bolton, Stephen Gaffney, Helen King, Demis Hassabis, Shane Legg, Stig Petersen
DeepMind Lab is a first-person 3D game platform designed for research and development of general artificial intelligence and machine learning systems.
3 code implementations • 15 Jul 2015 • Arun Nair, Praveen Srinivasan, Sam Blackwell, Cagdas Alcicek, Rory Fearon, Alessandro De Maria, Vedavyas Panneershelvam, Mustafa Suleyman, Charles Beattie, Stig Petersen, Shane Legg, Volodymyr Mnih, Koray Kavukcuoglu, David Silver
We present the first massively distributed architecture for deep reinforcement learning.
Ranked #17 on
Atari Games
on Atari 2600 Private Eye
no code implementations • 20 Dec 2007 • Shane Legg, Marcus Hutter
Finally, we survey the many other tests and definitions of intelligence that have been proposed for machines.