Taylor expansion policy optimization
Abstract
In this work, we investigate the application of Taylor expansions in reinforcement learning. In particular, we propose Taylor expansion policy optimization , a policy optimization formalism that generalizes prior work (e.g., TRPO) as a first-order special case. We also show that Taylor expansions intimately relate to off-policy evaluation. Finally, we show that this new formulation entails modifications which improve the performance of several state-of-the-art distributed algorithms.
Domains
Machine Learning [stat.ML]
Fichier principal
Taylor_expansion_policy_optimization__arxiv_ (3).pdf (765.05 Ko)
Télécharger le fichier
Origin : Files produced by the author(s)
Loading...