Risk-Sensitive Policy with Distributional Reinforcement Learning
Algorithms · 30.06.2023 · 16 (7) · 325
DOI: 10.3390/a16070325 ↗Kurz gefasst
Fachartikel in der Zeitschrift Algorithms, online erschienen am 30.06.2023. Verfasst von Thibaut Théate und 1 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Thibaut Théate.
Abstract (Originalsprache)
Classical reinforcement learning (RL) techniques are generally concerned with the design of decision-making policies driven by the maximisation of the expected outcome. Nevertheless, this approach does not take into consideration the potential risk associated with the actions taken, which may be critical in certain applications. To address that issue, the present research work introduces a novel methodology based on distributional RL to derive sequential decision-making policies that are sensitive to the risk, the latter being modelled by the tail of the return probability distribution. The core idea is to replace the Q function generally standing at the core of learning schemes in RL by another function, taking into account both the expected return and the risk. Named the risk-based utility function U, it can be extracted from the random return distribution Z naturally learnt by any distributional RL algorithm. This enables the spanning of the complete potential trade-off between risk minimisation and expected return maximisation, in contrast to fully risk-averse methodologies. Fundamentally, this research yields a truly practical and accessible solution for learning risk-sensitive policies with minimal modification to the distributional RL algorithm, with an emphasis on the interpretability of the resulting decision-making process.
Förderung
- Thibaut Théate
Zitieren
APA
Théate, T., & Ernst, D. (2023). Risk-Sensitive Policy with Distributional Reinforcement Learning. Algorithms, 16(7), 325. https://doi.org/10.3390/a16070325
Vancouver
Théate T, Ernst D. Risk-Sensitive Policy with Distributional Reinforcement Learning. Algorithms. 2023;16(7):325. doi:10.3390/a16070325
BibTeX
@article{Thate2023,
author = {Théate, Thibaut and Ernst, Damien},
title = {Risk-Sensitive Policy with Distributional Reinforcement Learning},
journal = {Algorithms},
year = {2023},
volume = {16},
number = {7},
pages = {325},
doi = {10.3390/a16070325}
}
EUVIMED