Adaptive Batch Size for Safe Policy Gradients

By Matteo Papini, Matteo Pirotta, Marcello Restelli. 2017

37 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Matteo Papini
2. Marcello Restelli
3. Matteo Pirotta
4. Damiano Binaghi
5. Giuseppe Canonaco
6. Paul Trichelair
7. Kamil Andrzej Ciosek
8. Rodrigo Nogueira

Citations in the corpus

• Safe Policy Improvement with Baseline Bootstrapping (2017, background): “(Papini et al., 2017) propose to adapt the batch size to ensure that the gradients safely improve the policy.”
• Safe Policy Improvement with an Estimated Baseline Policy (2019, neutral): “We also study the influence of the dataset size |D| ∈ [10, 20, 50, 100, 200, 500, 1000, 2000].”
• Stochastic Variance-Reduced Policy Gradient (2018, background): “Future work should also focus on making batch sizesN andB adaptive, as suggested in (Papini et al., 2017).”