no code implementations • 6 May 2024 • Xingyou Song, Yingtao Tian, Robert Tjarko Lange, Chansoo Lee, Yujin Tang, Yutian Chen
Their incorporation has been rapid and transformative, marking a significant paradigm shift in the field of machine learning research.
1 code implementation • 5 Mar 2024 • Robert Tjarko Lange, Yingtao Tian, Yujin Tang
Given a trajectory of evaluations and search distribution statistics, Evolution Transformer outputs a performance-improving update to the search distribution.
no code implementations • 28 Feb 2024 • Robert Tjarko Lange, Yingtao Tian, Yujin Tang
Large Transformer models are capable of implementing a plethora of so-called in-context learning algorithms.
1 code implementation • 8 Feb 2024 • Matthew Thomas Jackson, Chris Lu, Louis Kirsch, Robert Tjarko Lange, Shimon Whiteson, Jakob Nicolaus Foerster
We propose a simple augmentation to two existing objective discovery approaches that allows the discovered algorithm to dynamically update its objective function throughout the agent's training procedure, resulting in expressive schedules and increased generalization across different training horizons.
2 code implementations • 16 Nov 2023 • Alexander Rutherford, Benjamin Ellis, Matteo Gallici, Jonathan Cook, Andrei Lupu, Gardar Ingvarsson, Timon Willi, Akbir Khan, Christian Schroeder de Witt, Alexandra Souly, Saptarashmi Bandyopadhyay, Mikayel Samvelyan, Minqi Jiang, Robert Tjarko Lange, Shimon Whiteson, Bruno Lacerda, Nick Hawes, Tim Rocktaschel, Chris Lu, Jakob Nicolaus Foerster
This not only enables GPU acceleration, but also provides a more flexible MARL environment, unlocking the potential for self-play, meta-learning, and other future applications in MARL.
1 code implementation • NeurIPS 2023 • Robert Tjarko Lange, Yujin Tang, Yingtao Tian
Recently, the Deep Learning community has become interested in evolutionary optimization (EO) as a means to address hard optimization problems, e. g. meta-learning through long inner loop unrolls or optimizing non-differentiable operators.
1 code implementation • 31 May 2023 • Robert Tjarko Lange, Henning Sprekeler
Is the lottery ticket phenomenon an idiosyncrasy of gradient-based training or does it generalize to evolutionary optimization?
1 code implementation • 8 Apr 2023 • Robert Tjarko Lange, Tom Schaul, Yutian Chen, Chris Lu, Tom Zahavy, Valentin Dalibard, Sebastian Flennerhag
Genetic algorithms constitute a family of black-box optimization algorithms, which take inspiration from the principles of biological evolution.
2 code implementations • 8 Dec 2022 • Robert Tjarko Lange
In order to better harness these resources and to enable the next generation of black-box optimization algorithms, we release evosax: A JAX-based library of evolution strategies which allows researchers to leverage powerful function transformations such as just-in-time compilation, automatic vectorization and hardware parallelization.
1 code implementation • 21 Nov 2022 • Robert Tjarko Lange, Tom Schaul, Yutian Chen, Tom Zahavy, Valentin Dallibard, Chris Lu, Satinder Singh, Sebastian Flennerhag
Optimizing functions without access to gradients is the remit of black-box methods such as evolution strategies.
no code implementations • ICLR 2022 • Marc Aurel Vischer, Robert Tjarko Lange, Henning Sprekeler
But how is the performance of winning lottery tickets affected by the distributional shift inherent to reinforcement learning problems?
no code implementations • 9 Oct 2020 • Robert Tjarko Lange, Henning Sprekeler
Animals are equipped with a rich innate repertoire of sensory, behavioral and motor skills, which allows them to interact with the world immediately after birth.
no code implementations • 7 Oct 2019 • Petros Christodoulou, Robert Tjarko Lange, Ali Shafti, A. Aldo Faisal
From a young age humans learn to use grammatical principles to hierarchically combine words into sentences.
1 code implementation • 29 Jul 2019 • Robert Tjarko Lange, Aldo Faisal
By treating an on-policy trajectory as a sentence sampled from the policy-conditioned language of the environment, we identify hierarchical constituents with the help of unsupervised grammatical inference.