1 code implementation • 20 Nov 2022 • Chris Lu, Timon Willi, Alistair Letcher, Jakob Foerster
More specifically, we show that an ACT Adversary is capable of harming performance by interfering with the learner's function approximation, or instead helping the Victim's performance by outputting useful features.
1 code implementation • 11 Oct 2022 • Chris Lu, Jakub Grudzien Kuba, Alistair Letcher, Luke Metz, Christian Schroeder de Witt, Jakob Foerster
We refer to the immediate result as Learnt Policy Optimisation (LPO).
1 code implementation • 8 Mar 2022 • Timon Willi, Alistair Letcher, Johannes Treutlein, Jakob Foerster
Finally, in an empirical evaluation on a set of general-sum games, we find that COLA finds prosocial solutions and that it converges under a wider range of learning rates than HOLA and LOLA.
no code implementations • 16 Nov 2021 • Jeffrey Ma, Alistair Letcher, Florian Schäfer, Yuanyuan Shi, Anima Anandkumar
In this work we propose polymatrix competitive gradient descent (PCGD) as a method for solving general sum competitive optimization involving arbitrary numbers of agents.
no code implementations • NeurIPS 2020 • Jack Parker-Holder, Luke Metz, Cinjon Resnick, Hengyuan Hu, Adam Lerer, Alistair Letcher, Alex Peysakhovich, Aldo Pacchiano, Jakob Foerster
In the era of ever decreasing loss functions, SGD and its various offspring have become the go-to optimization tool in machine learning and are a key component of the success of deep neural networks (DNNs).
1 code implementation • ICLR 2021 • Alistair Letcher
Under mild regularity conditions, gradient-based methods converge globally to a critical point in the single-loss setting.
1 code implementation • 13 May 2019 • Alistair Letcher, David Balduzzi, Sebastien Racaniere, James Martens, Jakob Foerster, Karl Tuyls, Thore Graepel
The decomposition motivates Symplectic Gradient Adjustment (SGA), a new algorithm for finding stable fixed points in differentiable games.
no code implementations • ICLR 2019 • Alistair Letcher, Jakob Foerster, David Balduzzi, Tim Rocktäschel, Shimon Whiteson
A growing number of learning methods are actually differentiable games whose players optimise multiple, interdependent objectives in parallel -- from GANs and intrinsic curiosity to multi-agent RL.
no code implementations • 14 Nov 2017 • Alistair Letcher, Jelena Trišović, Collin Cademartori, Xi Chen, Jason Xu
Automatic conflict detection has grown in relevance with the advent of body-worn technology, but existing metrics such as turn-taking and overlap are poor indicators of conflict in police-public interactions.