Active reward learning and iterative trajectory improvement from comparative language feedback

Human-in-the-loop learning has gained traction in fields like robotics and natural language processing in recent years. While prior work mostly relies on human feedback in the form of preference comparisons, this feedback type has multiple limitations. It does not let users explain the reasons for their preferences and provides only a binary signal for learning, resulting in huge data inefficiency. Consequently, training robots require a substantial amount of human feedback, occupying significant time and burdening the user. To overcome these challenges, we take the insight that language is a preferable medium compared to comparisons, providing more information regarding user preferences. Thus, in this work, we aim to incorporate comparative language feedback to iteratively improve robot trajectories and learn reward functions that encode human preferences. We learn a shared latent space that integrates trajectory data and language feedback, and subsequently leverage the learned latent space to improve trajectories and learn human preferences. We finally introduce an active learning method that integrates comparative language feedback to further boost data-efficiency. Our results in simulation experiments and user studies demonstrate the effectiveness of the learned latent space and the success of our learning algorithms. Our reward learning algorithm exhibits a 23.9% improvement in subjective score on average and 11.3% higher time-efficiency compared to the preference comparison method in the user studies. Our active querying method further improves user experience featuring an 8.31% average improvement in subjective scores compared to random querying. Our code is publicly available at https://liralab.usc.edu/comparative-language-feedback/ .