相关论文: A New Item Response Theory Model for Open-Ended On…

Although there is now a large literature on policy evaluation and learning, much of the prior work assumes that the treatment assignment of one unit does not affect the outcome of another unit. Unfortunately, ignoring interference can lead…

Modern Large Language Models (LLMs) have shown rapid improvements in reasoning capabilities, driven largely by reinforcement learning (RL) with verifiable rewards. Here, we ask whether these LLMs can self-improve without the need for…

We are interested in solving the problem of imitation learning with a limited amount of real-world expert data. Existing offline imitation methods often struggle with poor data coverage and severe performance degradation. We propose a…

In two earlier studies, we developed a new method to measure students' ability to transfer physics problem solving skills to new contexts using a sequence of online learning modules, and implemented two interventions in the form of…

Language models (LMs) now excel at many tasks such as few-shot learning, question answering, reasoning, and dialog. However, they sometimes generate unsupported or misleading content. A user cannot easily determine whether their outputs are…

Despite the availability of benchmark machine learning (ML) repositories (e.g., UCI, OpenML), there is no standard evaluation strategy yet capable of pointing out which is the best set of datasets to serve as gold standard to test different…

Humans observe and interact with the world to acquire knowledge. However, most existing machine reading comprehension (MRC) tasks miss the interactive, information-seeking component of comprehension. Such tasks present models with static…

In Reinforcement Learning (RL), training a policy from scratch with online experiences can be inefficient because of the difficulties in exploration. Recently, offline RL provides a promising solution by giving an initialized offline…

A central capability of intelligent systems is the ability to continuously build upon previous experiences to speed up and enhance learning of new tasks. Two distinct research paradigms have studied this question. Meta-learning views this…

Large pre-trained language models help to achieve state of the art on a variety of natural language processing (NLP) tasks, nevertheless, they still suffer from forgetting when incrementally learning a sequence of tasks. To alleviate this…

We consider problems of making sequences of decisions to accomplish tasks, interacting via the medium of language. These problems are often tackled with reinforcement learning approaches. We find that these models do not generalize well…

Time series is the most prevalent form of input data for educational prediction tasks. The vast majority of research using time series data focuses on hand-crafted features, designed by experts for predictive performance and…

In natural language processing (NLP) we always rely on human judgement as the golden quality evaluation method. However, there has been an ongoing debate on how to better evaluate inter-rater reliability (IRR) levels for certain evaluation…

A key challenge in Imitation Learning (IL) is that optimal state actions demonstrations are difficult for the teacher to provide. For example in robotics, providing kinesthetic demonstrations on a robotic manipulator requires the teacher to…

We consider a Bayesian approach to offline model-based inverse reinforcement learning (IRL). The proposed framework differs from existing offline model-based IRL approaches by performing simultaneous estimation of the expert's reward…

On the one hand, a growing amount of research discusses support for improving online collaborative learning quality, and many indicators are focused to assess its success. On the other hand, thinkLets for designing reputable and valuable…

We propose a new online learning model for learning with preference feedback. The model is especially suited for applications like web search and recommender systems, where preference data is readily available from implicit user feedback…

Despite the considerable potential of reinforcement learning (RL), robotic control tasks predominantly rely on imitation learning (IL) due to its better sample efficiency. However, it is costly to collect comprehensive expert demonstrations…

We propose a new method to measure the task-specific accuracy of Retrieval-Augmented Large Language Models (RAG). Evaluation is performed by scoring the RAG on an automatically-generated synthetic exam composed of multiple choice questions…

Traditionally, reinforcement learning (RL) agents learn to solve new tasks by updating their neural network parameters through interactions with the task environment. However, recent works demonstrate that some RL agents, after certain…