Uniformly Conservative Exploration in Reinforcement Learning
A key challenge to deploying reinforcement learning in practice is avoiding excessive (harmful) exploration in individual episodes. We propose a natural constraint on exploration -- \textit{uniformly} outperforming a conservative policy (adaptively estimated from all data observed thus far), up to a...
Gespeichert in:
Hauptverfasser: | , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | A key challenge to deploying reinforcement learning in practice is avoiding
excessive (harmful) exploration in individual episodes. We propose a natural
constraint on exploration -- \textit{uniformly} outperforming a conservative
policy (adaptively estimated from all data observed thus far), up to a
per-episode exploration budget. We design a novel algorithm that uses a UCB
reinforcement learning policy for exploration, but overrides it as needed to
satisfy our exploration constraint with high probability. Importantly, to
ensure unbiased exploration across the state space, our algorithm adaptively
determines when to explore. We prove that our approach remains conservative
while minimizing regret in the tabular setting. We experimentally validate our
results on a sepsis treatment task and an HIV treatment task, demonstrating
that our algorithm can learn while ensuring good performance compared to the
baseline policy for every patient; the latter task also demonstrates that our
approach extends to continuous state spaces via deep reinforcement learning. |
---|---|
DOI: | 10.48550/arxiv.2110.13060 |