Related papers: Imitation learning for clinical decision support i…

We propose an approach to online model adaptation and control in the challenging case of hybrid and discontinuous dynamics where actions may lead to difficult-to-escape "trap" states, under a given controller. We first learn dynamics for a…

In real-world reinforcement learning applications the learner's observation space is ubiquitously high-dimensional with both relevant and irrelevant information about the task at hand. Learning from high-dimensional observations has been…

Predicting drug response in patients from preclinical data remains a major challenge in precision oncology due to the substantial biological gap between in vitro cell lines and patient tumors. Rather than aiming to improve absolute in vitro…

We introduce Extreme Quantum Cognition Machines, a class of quantum learning architectures for deliberative decision making that is tolerant to noisy and contradictory training data. Inspired by the quantum cognition paradigm, Extreme…

Recent work has shown diffusion models are an effective approach to learning the multimodal distributions arising from demonstration data in behavior cloning. However, a drawback of this approach is the need to learn a denoising function,…

Interventions are central to causal learning and reasoning. Yet ultimately an intervention is an abstraction: an agent embedded in a physical environment (perhaps modeled as a Markov decision process) does not typically come equipped with…

Leveraging the in-context learning (ICL) capability of Large Language Models (LLMs) for tabular classification has gained significant attention for its training-free adaptability across diverse datasets. Recent advancements, like TabPFN,…

Robotic manipulation often requires memory: occlusion and state changes can make decision-time observations perceptually aliased, making action selection non-Markovian at the observation level because the same observation may arise from…

Random delays weaken the temporal correspondence between actions and subsequent state feedback, making it difficult for agents to identify the true propagation process of action effects. In cross-task scenarios, changes in task objectives…

(Economic) nonlinear model predictive control ((e)NMPC) requires dynamic models that are sufficiently accurate and computationally tractable. Data-driven surrogate models for mechanistic models can reduce the computational burden of…

Accurate predictions, as with machine learning, may not suffice to provide optimal healthcare for every patient. Indeed, prediction can be driven by shortcuts in the data, such as racial biases. Causal thinking is needed for data-driven…

Model predictive control (MPC) is a popular approach for trajectory optimization in practical robotics applications. MPC policies can optimize trajectory parameters under kinodynamic and safety constraints and provide guarantees on safety,…

Recent foundation models for tabular data achieve strong task-specific performance via in-context learning. Nevertheless, they focus on direct prediction by encapsulating both representation learning and task-specific inference inside a…

Despite the impressive advancements achieved using deep-learning for functional brain activity analysis, the heterogeneity of functional patterns and scarcity of imaging data still pose challenges in tasks such as prediction of future onset…

We investigate model-based reinforcement learning in contextual Markov decision processes (C-MDPs) in which the context is unobserved and induces confounding in the offline dataset. In such settings, conventional model-learning methods are…

Learning-based methods have shown promising performance for accelerating motion planning, but mostly in the setting of static environments. For the more challenging problem of planning in dynamic environments, such as multi-arm assembly…

The goal of imitation learning is to mimic expert behavior without access to an explicit reward signal. Expert demonstrations provided by humans, however, often show significant variability due to latent factors that are typically not…

Conventional imitation learning assumes access to the actions of demonstrators, but these motor signals are often non-observable in naturalistic settings. Additionally, sequential decision-making behaviors in these settings can deviate from…

Humans often acquire new skills through observation and imitation. For robotic agents, learning from the plethora of unlabeled video demonstration data available on the Internet necessitates imitating the expert without access to its…

Offline reinforcement learning has shown promise for solving tasks in safety-critical settings, such as clinical decision support. Its application, however, has been limited by the lack of interpretability and interactivity for clinicians.…