Conservative Optimistic Policy Optimization via Multiple Importance Sampling
Reinforcement Learning (RL) has been able to solve hard problems such as playing Atari games or solving the game of Go, with a unified approach. Yet modern deep RL approaches are still not widely used in real-world applications. One reason could be the lack of guarantees on the performance of the in...
Gespeichert in:
Hauptverfasser: | , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Reinforcement Learning (RL) has been able to solve hard problems such as
playing Atari games or solving the game of Go, with a unified approach. Yet
modern deep RL approaches are still not widely used in real-world applications.
One reason could be the lack of guarantees on the performance of the
intermediate executed policies, compared to an existing (already working)
baseline policy. In this paper, we propose an online model-free algorithm that
solves conservative exploration in the policy optimization problem. We show
that the regret of the proposed approach is bounded by
$\tilde{\mathcal{O}}(\sqrt{T})$ for both discrete and continuous parameter
spaces. |
---|---|
DOI: | 10.48550/arxiv.2103.03307 |