A model-free posterior sampling algorithm for online RLHF is shown to achieve O(sqrt(T)) regret when the completed function class has low Bellman eluder dimension.
Preference-based online learning with dueling bandits: a survey.J
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Thompson Sampling in Online RLHF with General Function Approximation
A model-free posterior sampling algorithm for online RLHF is shown to achieve O(sqrt(T)) regret when the completed function class has low Bellman eluder dimension.