Being able to discover diverse useful skills without external reward functions is beneficial in reinforcement learning research. Previous unsupervised skill discovery approaches mainly train different skills in parallel. Although impressive results have been provided, we found that parallel training procedure can sometimes block exploration when the state visited by different skills overlap, which leads to poor state coverage and restricts the diversity of learned skills. In this paper, we take a deeper look into this phenomenon and propose a novel framework to address this issue, which we call Recurrent Skill Training (ReST). Instead of training all the skills in parallel, ReST trains different skills one after another recurrently, along with a state coverage based intrinsic reward.

We introduce Functional Diffusion Processes (FDPs), which generalize score-based diffusion models to infinite-dimensional function spaces. FDPs require a new mathematical framework to describe the forward and backward dynamics, and several extensions to derive practical training objectives. These include infinite-dimensional versions of Girsanov theorem, in order to be able to compute an ELBO, and of the sampling theorem, in order to guarantee that functional evaluations in a countable set of points are equivalent to infinite-dimensional functions. We use FDPs to build a new breed of generative models in function spaces, which do not require specialized network architectures, and that can work with any kind of continuous data.Our results on real data show that FDPs achieve high-quality image generation, using a simple MLP architecture with orders of magnitude fewer parameters than existing diffusion models.

Learning effective reinforcement learning (RL) policies to solve real-world complex tasks can be quite challenging without a high-fidelity simulation environment. In most cases, we are only given imperfect simulators with simplified dynamics, which inevitably lead to severe sim-to-real gaps in RL policy learning. The recently emerged field of offline RL provides another possibility to learn policies directly from pre-collected historical data. However, to achieve reasonable performance, existing offline RL algorithms need impractically large offline data with sufficient state-action space coverage for training. This brings up a new question: is it possible to combine learning from limited real data in offline RL and unrestricted exploration through imperfect simulators in online RL to address the drawbacks of both approaches?

Extending recent advances in Learning from Demonstration (LfD) frameworks to multi-robot settings poses critical challenges such as environment non-stationarity due to partial observability which is detrimental to the applicability of existing methods. Although prior work has shown that enabling communication among agents of a robot team can alleviate such issues, creating inter-agent communication under existing Multi-Agent LfD (MA-LfD) frameworks requires the human expert to provide demonstrations for both environment actions and communication actions, which necessitates an efficient communication strategy on a known message spaces. To address this problem, we propose Mixed-Initiative Multi-Agent Apprenticeship Learning (MixTURE). MixTURE enables robot teams to learn from a human expert-generated data a preferred policy to accomplish a collaborative task, while simultaneously learning emergent inter-agent communication to enhance team coordination. The key ingredient to MixTURE's success is automatically learning a communication policy, enhanced by a mutual-information maximizing reverse model that rationalizes the underlying expert demonstrations without the need for human generated data or an auxiliary reward function.

We derive a novel active learning algorithm in the streaming setting for binary classification tasks. The algorithm leverages weak labels to minimize the number of label requests, and trains a model to optimize a surrogate loss on a resulting set of labeled and weak-labeled points. Our algorithm jointly admits two crucial properties: theoretical guarantees in the general agnostic setting and a strong empirical performance. Our theoretical analysis shows that the algorithm attains favorable generalization and label complexity bounds, while our empirical study on 18 real-world datasets demonstrate that the algorithm outperforms standard baselines, including the Margin Algorithm, or Uncertainty Sampling, a high-performing active learning algorithm favored by practitioners.

Likewise, the current trend is to produce new resources in a digital format (e.g., in the context of social networks), which entails an in-depth paradigm shift in almost all the humanistic, social, scientific and technological fields. In particular, the field of the humanities is one which is going through a significant transformation as a result of these digitalization efforts and the paradigm shift associated with the digital age. Indeed, we are witnessing the emergence of a whole host of disciplines, those of Digital Humanities (Berry 2012), which are closely dependent on the production and proper organization of digital collections. As a result of the undoubted importance of digital collections in modern society, the search for effective and efficient methods to carry out the production, preservation and enhancement of such digital collections has become a key challenge in modern society (Calhoun, 2013). In particular, the annotation of resources with metadata that enables their proper cataloging, search, retrieval and use in different application scenarios is one of the key elements to ensuring the profitability of these collections of digital objects.

Knowledge tracing (KT) is a task that predicts students' future performance based on their historical learning interactions. With the rapid development of deep learning techniques, existing KT approaches follow a data-driven paradigm that uses massive problem-solving records to model students' learning processes. However, although the educational contexts contain various factors that may have an influence on student learning outcomes, existing public KT datasets mainly consist of anonymized ID-like features, which may hinder the research advances towards this field. Therefore, in this work, we present, \emph{XES3G5M}, a large-scale dataset with rich auxiliary information about questions and their associated knowledge components (KCs)\footnote{\label{ft:kc}A KC is a generalization of everyday terms like concept, principle, fact, or skill.}. The XES3G5M dataset is collected from a real-world online math learning platform, which contains 7,652 questions, and 865 KCs with 5,549,635 interactions from 18,066 students.

Imitation learning (IL) is a general learning paradigm for sequential decision-making problems. Interactive imitation learning, where learners can interactively query for expert annotations, has been shown to achieve provably superior sample efficiency guarantees compared with its offline counterpart or reinforcement learning. In this work, we study classification-based online imitation learning (abbrev. COIL) and the fundamental feasibility to design oracle-efficient regret-minimization algorithms in this setting, with a focus on the general non-realizable case. We make the following contributions: (1) we show that in the COIL problem, any proper online learning algorithm cannot guarantee a sublinear regret in general; (2) we propose Logger, an improper online learning algorithmic framework, that reduces COIL to online linear optimization, by utilizing a new definition of mixed policy class; (3) we design two oracle-efficient algorithms within the Logger framework that enjoy different sample and interaction round complexity tradeoffs, and show their improvements over behavior cloning; (4) we show that under standard complexity-theoretic assumptions, efficient dynamic regret minimization is infeasible in the Logger framework.

Generative AI and large language models (LLMs) are transforming security by automating many tasks being performed manually. With such automation changing the practice of security as we know it, it is imperative that we prepare future students for the technology landscape they will ultimately face. Towards this end, we describe an initial curriculum and course that attempts to show students how to apply generative AI in order to solve problems in security. By refocusing security education and training on aspects uniquely suited for humans and showing students how to leverage automation for the rest, we believe we can better align security education practices with generative AI as it evolves.

The emergence of the Internet-of-Things (IoT) sheds light on applying the machine teaching (MT) algorithms for online personalized education on home devices. This direction becomes more promising during the COVID-19 pandemic when in-person education becomes infeasible. However, as one of the most influential and practical MT paradigms, iterative machine teaching (IMT) is prohibited on IoT devices due to its inefficient and unscalable algorithms. IMT is a paradigm where a teacher feeds examples iteratively and intelligently based on the learner's status. In each iteration, current IMT algorithms greedily traverse the whole training set to find an example for the learner, which is computationally expensive in practice.