相关论文: Coactive Learning for Locally Optimal Problem Solv…

Many recent successful off-policy multi-agent reinforcement learning (MARL) algorithms for cooperative partially observable environments focus on finding factorized value functions, leading to convoluted network structures. Building on the…

While reinforcement learning (RL) holds great potential for decision making in the real world, it suffers from a number of unique difficulties which often need specific consideration. In particular: it is highly non-stationary; suffers from…

When humans interact with learning-based control systems, a common goal is to minimize a cost function known only to the human. For instance, an exoskeleton may adapt its assistance in an effort to minimize the human's metabolic…

We propose a novel planning technique for satisfying tasks specified in temporal logic in partially revealed environments. We define high-level actions derived from the environment and the given task itself, and estimate how each action…

An enormous and ever-growing volume of data is nowadays becoming available in a sequential fashion in various real-world applications. Learning in nonstationary environments constitutes a major challenge, and this problem becomes orders of…

Deep neural networks excel at comprehending complex visual signals, delivering on par or even superior performance to that of human experts. However, ad-hoc visual explanations of model decisions often reveal an alarming level of reliance…

We consider adaptive decision-making problems where an agent optimizes a cumulative performance objective by repeatedly choosing among a finite set of options. Compared to the classical prediction-with-expert-advice set-up, we consider…

Recent work has shown a variety of ways in which machine learning can be used to accelerate the solution of constrained optimization problems. Increasing demand for real-time decision-making capabilities in applications such as artificial…

We initiate the study of active learning algorithms for classifying strategic agents. Active learning is a well-established framework in machine learning in which the learner selectively queries labels, often achieving substantially higher…

Conventional learning with expert advice methods assumes a learner is always receiving the outcome (e.g., class labels) of every incoming training instance at the end of each trial. In real applications, acquiring the outcome from oracle…

We develop an online learning method for prediction, which is important in problems with large and/or streaming data sets. We formulate the learning approach using a covariance-fitting methodology, and show that the resulting predictor has…

Active perception describes a broad class of techniques that couple planning and perception systems to move the robot in a way to give the robot more information about the environment. In most robotic systems, perception is typically…

This paper presents a cloud-based learning model predictive controller that integrates three interacting components: a set of agents, which must learn to perform a finite set of tasks with the minimum possible local cost; a coordinator,…

Active learning aims to reduce the high labeling cost involved in training machine learning models on large datasets by efficiently labeling only the most informative samples. Recently, deep active learning has shown success on various…

Conventional active learning algorithms assume a single labeler that produces noiseless label at a given, fixed cost, and aim to achieve the best generalization performance for given classifier under a budget constraint. However, in many…

We explore an active learning approach for dynamic fair resource allocation problems. Unlike previous work that assumes full feedback from all agents on their allocations, we consider feedback from a select subset of agents at each epoch of…

We study the problem of learning sequential decision-making policies in settings with multiple state-action representations. Such settings naturally arise in many domains, such as planning (e.g., multiple integer programming formulations)…

In imitation learning, an agent learns how to behave in an environment with an unknown cost function by mimicking expert demonstrations. Existing imitation learning algorithms typically involve solving a sequence of planning or…

The problem of reinforcement learning is considered where the environment or the model undergoes a change. An algorithm is proposed that an agent can apply in such a problem to achieve the optimal long-time discounted reward. The algorithm…

Positive unlabeled (PU) learning is useful in various practical situations, where there is a need to learn a classifier for a class of interest from an unlabeled data set, which may contain anomalies as well as samples from unknown classes.…