相关论文: Human-Aligned Skill Discovery: Balancing Behaviour…
In reinforcement learning, pre-trained low-level skills have the potential to greatly facilitate exploration. However, prior knowledge of the downstream task is required to strike the right balance between generality (fine-grained control)…
Navigating human-populated environments without causing discomfort is a critical capability for socially-aware agents. While rule-based approaches offer interpretability through predefined psychological principles, they often lack…
There is a recent trend of applying multi-agent reinforcement learning (MARL) to train an agent that can cooperate with humans in a zero-shot fashion without using any human data. The typical workflow is to first repeatedly run self-play…
Despite remarkable achievements in artificial intelligence, the deployability of learning-enabled systems in high-stakes real-world environments still faces persistent challenges. For example, in safety-critical domains like autonomous…
In the field of unsupervised skill discovery (USD), a major challenge is limited exploration, primarily due to substantial penalties when skills deviate from their initial trajectories. To enhance exploration, recent methodologies employ…
Bimanual dexterous manipulation is a critical yet underexplored area in robotics. Its high-dimensional action space and inherent task complexity present significant challenges for policy learning, and the limited task diversity in existing…
The embedded sensors in widely used smartphones and other wearable devices make the data of human activities more accessible. However, recognizing different human activities from the wearable sensor data remains a challenging research…
Humans can leverage hierarchical structures to split a task into sub-tasks and solve problems efficiently. Both imitation and reinforcement learning or a combination of them with hierarchical structures have been proven to be an efficient…
There are an increasing number of domains in which artificial intelligence (AI) systems both surpass human ability and accurately model human behavior. This introduces the possibility of algorithmically-informed teaching in these domains…
Learning skills in open-world environments is essential for developing agents capable of handling a variety of tasks by combining basic skills. Online demonstration videos are typically long but unsegmented, making them difficult to segment…
Recent years have shown a growing interest in using haptic shared control (HSC) in teleoperated systems. In HSC, the application of virtual guiding forces decreases the user's control effort and improves execution time in various tasks,…
Work-Related Musculoskeletal Disorders continue to be a major challenge in industrial environments, leading to reduced workforce participation, increased healthcare costs, and long-term disability. This study introduces a human-sensitive…
Modern applications increasingly require unsupervised learning of latent dynamics from high-dimensional time-series. This presents a significant challenge of identifiability: many abstract latent representations may reconstruct…
Recent advances in machine learning have shown that Reinforcement Learning from Human Feedback (RLHF) can improve machine learning models and align them with human preferences. Although very successful for Large Language Models (LLMs),…
As AI adoption expands across human society, the problem of aligning AI models to match human preferences remains a grand challenge. Currently, the AI alignment field is deeply divided between behavioral and representational approaches,…
Shared-autonomy imitation learning lets a human correct a robot in real time, mitigating covariate-shift errors. Yet existing approaches ignore two critical factors: (i) the operator's cognitive load and (ii) the risk created by delayed or…
Our society is governed by a set of norms which together bring about the values we cherish such as safety, fairness or trustworthiness. The goal of value-alignment is to create agents that not only do their tasks but through their…
Existing self-supervised learning methods learn representation by means of pretext tasks which are either (1) discriminating that explicitly specify which features should be separated or (2) aligning that precisely indicate which features…
Robots should be able to learn complex behaviors from human demonstrations. In practice, these human-provided datasets are inevitably imbalanced: i.e., the human demonstrates some subtasks more frequently than others. State-of-the-art…
We present a reinforcement learning based framework for human-centered collaborative systems. The framework is proactive and balances the benefits of timely actions with the risk of taking improper actions by minimizing the total time spent…