相关论文: Inverse Behavioral Optimization of QALY-Based Ince…

Imbalanced and small data regimes are pervasive in domains such as rare disease imaging, genomics, and disaster response, where labeled samples are scarce and naive augmentation often introduces artifacts. Existing solutions such as…

Background: Chronic diseases impose a sustained burden on healthcare systems through progressive deterioration and long-term costs. Although adherence-enhancing interventions are widely promoted, their return on investment (ROI) remains…

Current approaches to embodied AI tend to learn policies from expert demonstrations. However, without a mechanism to evaluate the quality of demonstrated actions, they are limited to learning from optimal behaviour, or they risk replicating…

As generative agents become increasingly capable, alignment of their behavior with complex human values remains a fundamental challenge. Existing approaches often simplify human intent through reduction to a scalar reward, overlooking the…

Bayesian inference over the reward presents an ideal solution to the ill-posed nature of the inverse reinforcement learning problem. Unfortunately current methods generally do not scale well beyond the small tabular setting due to the need…

Driving behavior modeling is of great importance for designing safe, smart, and personalized autonomous driving systems. In this paper, an internal reward function-based driving model that emulates the human's decision-making mechanism is…

Deep learning in small and imbalanced biomedical datasets remains fundamentally constrained by unstable optimization and poor generalization. We present the first biomedical implementation of FOSSIL (Flexible Optimization via…

The problem of inverse reinforcement learning (IRL) is relevant to a variety of tasks including value alignment and robot learning from demonstration. Despite significant algorithmic contributions in recent years, IRL remains an ill-posed…

This paper proposes a reversible learning framework to improve the robustness and efficiency of value based Reinforcement Learning agents, addressing vulnerability to value overestimation and instability in partially irreversible…

The quest for interpretable reinforcement learning is a grand challenge for the deployment of autonomous decision-making systems in safety-critical applications. Modern deep reinforcement learning approaches, while powerful, tend to produce…

The goal of inverse reinforcement learning (IRL) is to infer a reward function that explains the behavior of an agent performing a task. The assumption that most approaches make is that the demonstrated behavior is near-optimal. In many…

The increasing deployment of artificial intelligence (AI) in clinical settings challenges foundational assumptions underlying traditional frameworks of medical evidence. Classical statistical approaches, centered on randomized controlled…

Inverse reinforcement learning (IRL), which infers reward functions from demonstrations, is a valuable tool for modeling and understanding decision-making behavior. Many variants of IRL have been developed to capture complexities of human…

We present Causal Amortized Active Structure Learning (CAASL), an active intervention design policy that can select interventions that are adaptive, real-time and that does not require access to the likelihood. This policy, an amortized…

Inverse Reinforcement Learning (IRL) is attractive in scenarios where reward engineering can be tedious. However, prior IRL algorithms use on-policy transitions, which require intensive sampling from the current policy for stable and…

Globally, the outbreaks of infectious diseases have exerted an extremely profound and severe influence on health security and the economy. During the critical phases of epidemics, devising effective intervention measures poses a significant…

Personalized decision systems in healthcare and behavioral support often rely on static rule-based or engagement-maximizing heuristics that overlook users' emotional context and ethical constraints. Such approaches risk recommending…

Policy learning utilizing observational data is pivotal across various domains, with the objective of learning the optimal treatment assignment policy while adhering to specific constraints such as fairness, budget, and simplicity. This…

Inverse optimal control can be used to characterize behavior in sequential decision-making tasks. Most existing work, however, is limited to fully observable or linear systems, or requires the action signals to be known. Here, we introduce…

Adaptive behavior in volatile environments requires agents to switch among value-control regimes across latent contexts, but maintaining separate preferences, policy biases, and action-confidence parameters for every situation is…