相关论文: Is Imitation All You Need? Generalized Decision-Ma…

Despite increasing attention paid to the need for fast, scalable methods to analyze next-generation neuroscience data, comparatively little attention has been paid to the development of similar methods for behavioral analysis. Just as the…

While robot learning has demonstrated promising results for enabling robots to automatically acquire new skills, a critical challenge in deploying learning-based systems is scale: acquiring enough data for the robot to effectively…

Imitation learning is a powerful tool for training robot manipulation policies, allowing them to learn from expert demonstrations without manual programming or trial-and-error. However, common methods of data collection, such as human…

An important feature of pervasive, intelligent assistance systems is the ability to dynamically adapt to the current needs of their users. Hence, it is critical for such systems to be able to recognize those goals and needs based on…

LLMs are typically trained to answer user questions or follow instructions similarly to how human experts respond. However, in the standard alignment framework they lack the basic ability of explicit thinking before answering. Thinking is…

Learning from small data sets is critical in many practical applications where data collection is time consuming or expensive, e.g., robotics, animal experiments or drug design. Meta learning is one way to increase the data efficiency of…

There is a recent surge in interest for imitation learning, with large human video-game and robotic manipulation datasets being used to train agents on very complex tasks. While deep neuroevolution has recently been shown to match the…

Reinforcement learning has the potential to automate the acquisition of behavior in complex settings, but in order for it to be successfully deployed, a number of practical challenges must be addressed. First, in real world settings, when…

Person re-identification plays a significant role in realistic scenarios due to its various applications in public security and video surveillance. Recently, leveraging the supervised or semi-unsupervised learning paradigms, which benefits…

Gradient-based meta-learners such as MAML are able to learn a meta-prior from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. One important limitation of such frameworks is that they seek a common…

Learning to learn is a powerful paradigm for enabling models to learn from data more effectively and efficiently. A popular approach to meta-learning is to train a recurrent model to read in a training dataset as input and output the…

We tackle the challenges of synthesizing versatile, physically simulated human motions for full-body object manipulation. Unlike prior methods that are focused on detailed motion tracking, trajectory following, or teleoperation, our…

Recently, motion generation by machine learning has been actively researched to automate various tasks. Imitation learning is one such method that learns motions from data collected in advance. However, executing long-term tasks remains…

When tackling complex problems, humans naturally break them down into smaller, manageable subtasks and adjust their initial plans based on observations. For instance, if you want to make coffee at a friend's place, you might initially plan…

As robots become more integrated in society, their ability to coordinate with other robots and humans on multi-modal tasks (those with multiple valid solutions) is crucial. Such behaviors can be learned from expert demonstrations via…

Despite rapid progress in autonomous robotics, executing complex or long-horizon tasks remains a fundamental challenge. Most current approaches follow an open-loop paradigm with limited reasoning and no feedback, resulting in poor…

In this paper, we study the problem of enabling a vision-based robotic manipulation system to generalize to novel tasks, a long-standing challenge in robot learning. We approach the challenge from an imitation learning perspective, aiming…

Critical sectors of human society are progressing toward the adoption of powerful artificial intelligence (AI) agents, which are trained individually on behalf of self-interested principals but deployed in a shared environment. Short of…

People's decisions about how to allocate their limited computational resources are essential to human intelligence. An important component of this metacognitive ability is deciding whether to continue thinking about what to do and move on…

Imitation learning is a class of promising policy learning algorithms that is free from many practical issues with reinforcement learning, such as the reward design issue and the exploration hardness. However, the current imitation…