Value estimation is a critical component of the reinforcement learning (RL) paradigm. The question of how to effectively learn value predictors from data is one of the major problems studied by the RL community, and different approaches exploit structure in the problem domain in different ways. Model learning can make use of the rich transition structure present in sequences of observations, but this approach is usually not sensitive to the reward function. In contrast, model-free methods directly leverage the quantity of interest from the future, but receive a potentially weak scalar signal (an estimate of the return). We develop an approach for representation learning in RL that sits in between these two extremes: we propose to learn what to model in a way that can directly help value prediction.

Our interpretation of value concepts is shaped by our sociocultural background and lived experiences, and is thus subjective. Recognizing individual value interpretations is important for developing AI systems that can align with diverse human perspectives and avoid bias toward majority viewpoints. To this end, we investigate whether a language model can predict individual value interpretations by leveraging multi-dimensional subjective annotations as a proxy for their interpretive lens. That is, we evaluate whether providing examples of how an individual annotates Sentiment, Emotion, Argument, and Topics (SEAT dimensions) helps a language model in predicting their value interpretations. Our experiment across different zero- and few-shot settings demonstrates that providing all SEAT dimensions simultaneously yields superior performance compared to individual dimensions and a baseline where no information about the individual is provided. Furthermore, individual variations across annotators highlight the importance of accounting for the incorporation of individual subjective annotators. To the best of our knowledge, this controlled setting, although small in size, is the first attempt to go beyond demographics and investigate the impact of annotation behavior on value prediction, providing a solid foundation for future large-scale validation.

Aggregating multiple annotations into a single ground truth label may hide valuable insights into annotator disagreement, particularly in tasks where subjectivity plays a crucial role. In this work, we explore methods for identifying subjectivity in recognizing the human values that motivate arguments. We evaluate two main approaches: inferring subjectivity through value prediction vs. directly identifying subjectivity. Our experiments show that direct subjectivity identification significantly improves the model performance of flagging subjective arguments. Furthermore, combining contrastive loss with binary cross-entropy loss does not improve performance but reduces the dependency on per-label subjectivity. Our proposed methods can help identify arguments that individuals may interpret differently, fostering a more nuanced annotation process.

V alue estimation is a critical component of the reinforcement learning (RL) paradigm.

V alue estimation is a critical component of the reinforcement learning (RL) paradigm.

Despite these successes, applying RL techniques to complex control problems remains a daunting undertaking, where initial attempts often result in underwhelming performance.

Category-level generalization for robotic garment manipulation, such as bimanual smoothing, remains a significant hurdle due to high dimensionality, complex dynamics, and intra-category variations. Current approaches often struggle, either overfitting with concurrently learned visual features for a specific instance or, despite category-level perceptual generalization, failing to predict the value of synergistic bimanual actions. We propose the Feature-Conditioned Bimanual Value Network (FCBV-Net), operating on 3D point clouds to specifically enhance category-level policy generalization for garment smoothing. FCBV-Net conditions bimanual action value prediction on pre-trained, frozen dense geometric features, ensuring robustness to intra-category garment variations. Trainable downstream components then learn a task-specific policy using these static features. In simulated GarmentLab experiments with the CLOTH3D dataset, FCBV-Net demonstrated superior category-level generalization. It exhibited only an 11.5% efficiency drop (Steps80) on unseen garments compared to 96.2% for a 2D image-based baseline, and achieved 89% final coverage, outperforming an 83% coverage from a 3D correspondence-based baseline that uses identical per-point geometric features but a fixed primitive. These results highlight that the decoupling of geometric understanding from bimanual action value learning enables better category-level generalization.

Modern driving involves interactive technologies that can divert attention, increasing the risk of accidents. This paper presents a computational cognitive model that simulates human multitasking while driving. Based on optimal supervisory control theory, the model predicts how multitasking adapts to variations in driving demands, interactive tasks, and automation levels. Unlike previous models, it accounts for context-dependent multitasking across different degrees of driving automation. The model predicts longer in-car glances on straight roads and shorter glances during curves. It also anticipates increased glance durations with driver aids such as lane-centering assistance and their interaction with environmental demands. Validated against two empirical datasets, the model offers insights into driver multitasking amid evolving in-car technologies and automation.