Sign-SZPO: Provable Preference-based Reinforcement Learning with an Unknown Link Function

arXiv:2506.03066v2 Announce Type: replace Abstract: 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.

Abstract: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.

Machine Learning (cs.LG); Machine Learning (stat.ML)

arXiv:2506.03066 [cs.LG]

(or arXiv:2506.03066v2 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2506.03066 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

aiqbench analysis

Sign-SZPO: Provable Preference-based Reinforcement Learning with an Unknown Link Function

Related coverage