Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Pragmatic Feature Preferences: Learning Reward-Relevant Preferences from Human Input

About

Humans use social context to specify preferences over behaviors, i.e. their reward functions. Yet, algorithms for inferring reward models from preference data do not take this social learning view into account. Inspired by pragmatic human communication, we study how to extract fine-grained data regarding why an example is preferred that is useful for learning more accurate reward models. We propose to enrich binary preference queries to ask both (1) which features of a given example are preferable in addition to (2) comparisons between examples themselves. We derive an approach for learning from these feature-level preferences, both for cases where users specify which features are reward-relevant, and when users do not. We evaluate our approach on linear bandit settings in both vision- and language-based domains. Results support the efficiency of our approach in quickly converging to accurate rewards with fewer comparisons vs. example-only labels. Finally, we validate the real-world applicability with a behavioral experiment on a mushroom foraging task. Our findings suggest that incorporating pragmatic feature preferences is a promising approach for more efficient user-aligned reward learning.

Andi Peng, Yuying Sun, Tianmin Shu, David Abel• 2024

Related benchmarks

TaskDatasetResultRank
Reward AccuracyManiSkill 4-task In Distribution
Pick Reward Accuracy99.3
5
Reward AccuracyManiSkill 2-task Color Swapped OOD
Pick Reward Accuracy62
5
Reward AccuracyManiSkill 4-task (Color Swapped OOD)
Pick Accuracy70
5
Reward PredictionManiSkill image-based 2-task Color Swapped (OOD)
Pick Success Rate29
5
Reward PredictionManiSkill (image-based) 4-task Color Swapped (OOD)
Pick Score80.7
5
Reward PredictionManiSkill image-based 2-task In Distribution
Pick Score84.7
5
Reward PredictionManiSkill image-based 4-task In Distribution
Pick Score86.7
5
Reward AccuracyManiSkill In Distribution 2
Reward Accuracy (Pick)94
5
Preference PredictionMeta-World Push-Wall (train)
Reward Accuracy90
4
Preference PredictionMeta-World Push (train)
Reward Accuracy87
4
Showing 10 of 12 rows

Other info

Follow for update