The authors propose IDS-based RLHF algorithms with a surrogate environment and a new ℓ_g distance, proving Bayesian regret bounds of order O(H^(3/2) sqrt(T log K)).
For the first term in Eqn.(A.3), using the basic fact thatA − λB/2 ≤ A2/2λB for B, λ≥ 0, we have Et V eE ∗ t 1,π∗ E (st
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Sample-Efficient Reinforcement Learning from Human Feedback via Information-Directed Sampling
The authors propose IDS-based RLHF algorithms with a surrogate environment and a new ℓ_g distance, proving Bayesian regret bounds of order O(H^(3/2) sqrt(T log K)).