This is the pre-proceedings for the RLC 2026. You may expect minor changes.
Reinforcement Learning Journal, vol. 7, 2026, pp. TBD.
Will be presented at the Reinforcement Learning Conference (RLC), Montréal, Quebec, Canada, August 15–17, 2026.
Keywords: reinforcement learning theory, preference-based reinforcement learning, unknown link
The link function, which characterizes the relationship between the preference for two trajectories and their returns, is a crucial component in designing RL algorithms that learn from preference feedback. Most existing methods, both theoretical and empirical, assume that the link function is known (often a logistic function based on the Bradley-Terry model), which is arguably restrictive given the complex nature of preferences, especially those of humans. To avoid mis-specification, this paper studies preference-based RL with an unknown link function and proposes a novel zeroth-order policy optimization algorithm called Sign-SZPO. Unlike typical zeroth-order methods, which rely on the known link function to estimate the value function differences and form a gradient estimator, Sign-SZPO only estimates the sign of the value function difference. It then constructs a parameter update direction that is positively correlated with the true policy gradient, eliminating the need to know the link function exactly. Under mild conditions, Sign-SZPO provably converges to a stationary policy with a polynomial rate in the number of policy iterations and trajectories per iteration. Empirical evaluations further demonstrate the robustness of Sign-SZPO under link function mis-specifications.
Qining Zhang and Lei Ying. "Sign-SZPO: Provable Preference-based Reinforcement Learning with an Unknown Link Function." Reinforcement Learning Journal, vol. 7, 2026, pp. TBD.
BibTeX:@article{zhang2026signszpo,
title={Sign-SZPO: Provable Preference-based Reinforcement Learning with an Unknown Link Function},
author={Qining Zhang and Lei Ying},
journal={Reinforcement Learning Journal},
volume={7},
pages={},
year={2026}
}