1 code implementation • 17 Dec 2023 • Dominik Schmidt, Minqi Jiang
LAPO takes a first step towards pre-training powerful, generalist policies and world models on the vast amounts of videos readily available on the web.
1 code implementation • 19 Nov 2021 • Dominik Schmidt, Thomas Schmied
This paper's contribution is threefold: We (1) propose an improved version of Rainbow, seeking to drastically reduce Rainbow's data, training time, and compute requirements while maintaining its competitive performance; (2) we empirically demonstrate the effectiveness of our approach through experiments on the Arcade Learning Environment, and (3) we conduct a number of ablation studies to investigate the effect of the individual proposed modifications.
no code implementations • ICLR 2021 • Dominik Schmidt, Georgia Koppe, Zahra Monfared, Max Beutelspacher, Daniel Durstewitz
A main theoretical interest in biology and physics is to identify the nonlinear dynamical system (DS) that generated observed time series.
no code implementations • 25 Sep 2019 • Dominik Schmidt, Georgia Koppe, Max Beutelspacher, Daniel Durstewitz
Vanilla RNN with ReLU activation have a simple structure that is amenable to systematic dynamical systems analysis and interpretation, but they suffer from the exploding vs. vanishing gradients problem.