New, formal definition of agency gives clear principles for causal modelling of AI agents and the incentives they face. Crossposted to our Deepmind blog. See also our extended blogpost on LessWrong/Alignment Forum. We want to build safe, aligned artificial general intelligence (AGI) systems that pursue the intended goals of its…

By Rob Brekelmans, Tim Genewein, Jordi Grau-Moya, Grégoire Delétang, Markus Kunesch, Shane Legg, Pedro A. Ortega Full paper, published in TMLR, here: arxiv.org/abs/2203.12592, OpenReview TL;DR: Policy regularisation can be interpreted as learning a strategy in the face of an imagined adversary; a decision-making principle which leads to robust policies. …

By Matthew Rahtz, Vikrant Varma, Ramana Kumar, Zachary Kenton, Shane Legg, and Jan Leike. Tl;dr: ReQueST is an algorithm for learning objectives from human feedback on hypothetical behaviour. In this work, we scale ReQueST to complex 3D environments, and show that it works even with feedback sourced entirely from real…

By the Safety Analysis Team: Grégoire Delétang, Jordi Grau-Moya, Markus Kunesch, Tim Genewein, Rob Brekelmans, Shane Legg, and Pedro A. Ortega Read our paper here: https://arxiv.org/abs/2111.02907 We’re all familiar with risk-sensitive choices. As you look out of the window, you see a few gray clouds and no rain, but decide…

By Tom Everitt, Ryan Carey, Lewis Hammond, James Fox, Eric Langlois, and Shane Legg Crossposted to the alignmentforum About 2 years ago, we released the first few papers on understanding agent incentives using causal influence diagrams. This blog post will summarize progress made since then. What are causal influence diagrams? A key problem in AI…

By Adam Gleave, Michael Dennis, Shane Legg, Stuart Russell and Jan Leike. TL;DR: Equivalent-Policy Invariant Comparison (EPIC) provides a fast and reliable way to compute how similar a pair of reward functions are to one another. EPIC can be used to benchmark reward learning algorithms by comparing learned reward functions…

By Zachary Kenton, Tom Everitt, Laura Weidinger, Iason Gabriel, Vladimir Mikulik and Geoffrey Irving Would your AI deceive you? This is a central question when considering the safety of AI, underlying many of the most pressing risks from current systems to future AGI. We have recently seen impressive advances in…

By the Safety Analysis Team: Grégoire Déletang, Jordi Grau-Moya, Miljan Martic, Tim Genewein, Tom McGrath, Vladimir Mikulik, Markus Kunesch, Shane Legg, and Pedro A. Ortega. TL;DR: To study agent behaviour we must use the tools of causal analysis rather than rely on observation alone. …

By Grégoire Delétang, Tom McGrath, Tim Genewein, Vladimir Mikulik, Markus Kunesch, Jordi Grau-Moya, Miljan Martic, Shane Legg, Pedro A. Ortega TL;DR: In our recent paper we show that meta-trained recurrent neural networks implement Bayes-optimal algorithms. One of the most challenging problems in modern AI research is understanding the learned algorithms…