Optimizing Algorithms From Pairwise User Preferences
Typical black-box optimization approaches in robotics focus on learning from metric scores. However, that is not always possible, as not all developers have ground truth available. Learning appropriate robot behavior in human-centric contexts often requires querying users, who typically cannot provide precise metric scores. Existing approaches leverage human feedback in an attempt to model an implicit reward function; however, this reward may be difficult or impossible to effectively capture. In this work, we introduce SortCMA to optimize algorithm parameter configurations in high dimensions based on pairwise user preferences. SortCMA efficiently and robustly leverages user input to find parameter sets without directly modeling a reward. We apply this method to tuning a commercial depth sensor without ground truth, and to robot social navigation, which involves highly complex preferences over robot behavior. We show that our method succeeds in optimizing for the user's goals and perform a user study to evaluate social navigation results.
Code (0)
등록된 구현이 없습니다.
Tasks
Social NavigationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Direct Preference Optimization with Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences
Reinforcement Learning from Human Feedback (RLHF) has become central to aligning large language models with human values, typically by first learning a reward model from preference data which is then used to update the m…
Reinforcement LearningPersonalized Preference Fine-tuning of Diffusion Models
RLHF techniques like DPO can significantly improve the generation quality of text-to-image diffusion models. However, these methods optimize for a single reward that aligns model generation with population-level preferen…
Collaborative Gaussian Processes for Preference Learning
We present a new model based on Gaussian processes (GPs) for learning pairwise preferences expressed by multiple users. Inference is simplified by using a \emph{preference kernel} for GPs which allows us to combine super…
Active LearningDimensionality ReductionGaussian ProcessesClustering and Inference From Pairwise Comparisons
Given a set of pairwise comparisons, the classical ranking problem computes a single ranking that best represents the preferences of all users. In this paper, we study the problem of inferring individual preferences, ari…
ClusteringReinforcement Learning with Pairwise Preferences in Long-Term Decision Problems
Reinforcement learning with scalar rewards is widely used for aligning machine-learning systems with user preferences. But, pairwise preferences are often more natural for users to specify than scalar rewards, and they e…
Reinforcement Learning