Deep Reinforcement Learning and the Deadly Triad - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2018

Deep Reinforcement Learning and the Deadly Triad

Résumé

We know from reinforcement learning theory that temporal difference learning can fail in certain cases. Sutton and Barto (2018) identify a deadly triad of function approximation, bootstrapping, and off-policy learning. When these three properties are combined, learning can diverge with the value estimates becoming unbounded. However, several algorithms successfully combine these three properties, which indicates that there is at least a partial gap in our understanding. In this work, we investigate the impact of the deadly triad in practice, in the context of a family of popular deep reinforcement learning models - deep Q-networks trained with experience replay - analysing how the components of this system play a role in the emergence of the deadly triad, and in the agent's performance

Dates et versions

hal-01949304 , version 1 (10-12-2018)

Identifiants

Citer

Hado van Hasselt, Yotam Doron, Florian Strub, Matteo Hessel, Nicolas Sonnerat, et al.. Deep Reinforcement Learning and the Deadly Triad. 2018. ⟨hal-01949304⟩
329 Consultations
1 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More