Learning by Doing: Controlling a Dynamical System using Causality, Control, and Reinforcement Learning
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Standard
Learning by Doing : Controlling a Dynamical System using Causality, Control, and Reinforcement Learning. / Weichwald, Sebastian; Wengel Mogensen, Søren; Lee, Tabitha Edith; Baumann, Dominik ; Kroemer, Oliver ; Guyon, Isabelle ; Trimpe, Sebastian; Peters, Jonas Martin; Pfister, Niklas Andreas.
Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track. PMLR, 2022. s. 246-258 (Proceedings of Machine Learning Research, Bind 176).Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Learning by Doing
T2 - 35th Conference on Neural Information Processing Systems (NeurIPS 2021)
AU - Weichwald, Sebastian
AU - Wengel Mogensen, Søren
AU - Lee, Tabitha Edith
AU - Baumann, Dominik
AU - Kroemer, Oliver
AU - Guyon, Isabelle
AU - Trimpe, Sebastian
AU - Peters, Jonas Martin
AU - Pfister, Niklas Andreas
PY - 2022
Y1 - 2022
N2 - Questions in causality, control, and reinforcement learning go beyond the classical machine learning task of prediction under i.i.d. observations. Instead, these fields consider the problem of learning how to actively perturb a system to achieve a certain effect on a response variable. Arguably, they have complementary views on the problem: In control, one usually aims to first identify the system by excitation strategies to then apply model-based design techniques to control the system. In (non-model-based) reinforcement learning, one directly optimizes a reward. In causality, one focus is on identifiability of causal structure. We believe that combining the different views might create synergies and this competition is meant as a first step toward such synergies. The participants had access to observational and (offline) interventional data generated by dynamical systems. Track CHEM considers an open-loop problem in which a single impulse at the beginning of the dynamics can be set, while Track ROBO considers a closed-loop problem in which control variables can be set at each time step. The goal in both tracks is to infer controls that drive the system to a desired state. Code is open-sourced ( https://github.com/LearningByDoingCompetition/learningbydoing-comp ) to reproduce the winning solutions of the competition and to facilitate trying out new methods on the competition tasks.Cite this Paper
AB - Questions in causality, control, and reinforcement learning go beyond the classical machine learning task of prediction under i.i.d. observations. Instead, these fields consider the problem of learning how to actively perturb a system to achieve a certain effect on a response variable. Arguably, they have complementary views on the problem: In control, one usually aims to first identify the system by excitation strategies to then apply model-based design techniques to control the system. In (non-model-based) reinforcement learning, one directly optimizes a reward. In causality, one focus is on identifiability of causal structure. We believe that combining the different views might create synergies and this competition is meant as a first step toward such synergies. The participants had access to observational and (offline) interventional data generated by dynamical systems. Track CHEM considers an open-loop problem in which a single impulse at the beginning of the dynamics can be set, while Track ROBO considers a closed-loop problem in which control variables can be set at each time step. The goal in both tracks is to infer controls that drive the system to a desired state. Code is open-sourced ( https://github.com/LearningByDoingCompetition/learningbydoing-comp ) to reproduce the winning solutions of the competition and to facilitate trying out new methods on the competition tasks.Cite this Paper
M3 - Article in proceedings
T3 - Proceedings of Machine Learning Research
SP - 246
EP - 258
BT - Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track
PB - PMLR
Y2 - 6 December 2021 through 14 December 2021
ER -
ID: 345421821