Abstract
Taylor expansion policy optimization generalizes TRPO and enhances off-policy evaluation and state-of-the-art distributed reinforcement learning algorithms.
AI-generated summary
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.
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2003.06259 in a model README.md to link it from this page.
Datasets citing this paper 1
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2003.06259 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a
collection
to link it from this page.