Reinforcement learning (RL) presents a promising framework to learn policies through environment interaction, but often requires an infeasible amount of interaction data to solve complex tasks from sparse rewards. One direction includes augmenting RL with offline data demonstrating desired tasks, but past work often require a lot of high-quality demonstration data that is difficult to obtain, especially for domains such as robotics. Our approach consists of a reverse curriculum followed by a forward curriculum. Unique to our approach compared to past work is the ability to efficiently leverage more than one demonstration via a per-demonstration reverse curriculum generated via state resets. The result of our reverse curriculum is an initial policy that performs well on a narrow initial state distribution and helps overcome difficult exploration problems. A forward curriculum is then used to accelerate the training of the initial policy to perform well on the full initial state distribution of the task and improve demonstration and sample efficiency. We show how the combination of a reverse curriculum and forward curriculum in our method, RFCL, enables significant improvements in demonstration and sample efficiency compared against various state-of-the-art learning-from-demonstration baselines, even solving previously unsolvable tasks that require high precision and control.

We study a Federated Reinforcement Learning (FedRL) problem with constraint heterogeneity. In our setting, we aim to solve a reinforcement learning problem with multiple constraints while $N$ training agents are located in $N$ different environments with limited access to the constraint signals and they are expected to collaboratively learn a policy satisfying all constraint signals. Such learning problems are prevalent in scenarios of Large Language Model (LLM) fine-tuning and healthcare applications. To solve the problem, we propose federated primal-dual policy optimization methods based on traditional policy gradient methods. Specifically, we introduce $N$ local Lagrange functions for agents to perform local policy updates, and these agents are then scheduled to periodically communicate on their local policies. Taking natural policy gradient (NPG) and proximal policy optimization (PPO) as policy optimization methods, we mainly focus on two instances of our algorithms, ie, {FedNPG} and {FedPPO}. We show that FedNPG achieves global convergence with an $\tilde{O}(1/\sqrt{T})$ rate, and FedPPO efficiently solves complicated learning tasks with the use of deep neural networks.

This paper presents reports on a series of experiments with a novel dataset evaluating how well Large Language Models (LLMs) can mark (i.e. grade) open text responses to short answer questions, Specifically, we explore how well different combinations of GPT version and prompt engineering strategies performed at marking real student answers to short answer across different domain areas (Science and History) and grade-levels (spanning ages 5-16) using a new, never-used-before dataset from Carousel, a quizzing platform. We found that GPT-4, with basic few-shot prompting performed well (Kappa, 0.70) and, importantly, very close to human-level performance (0.75). This research builds on prior findings that GPT-4 could reliably score short answer reading comprehension questions at a performance-level very close to that of expert human raters. The proximity to human-level performance, across a variety of subjects and grade levels suggests that LLMs could be a valuable tool for supporting low-stakes formative assessment tasks in K-12 education and has important implications for real-world education delivery.

This paper presents the use of Retrieval Augmented Generation (RAG) to improve the feedback generated by Large Language Models for programming tasks. For this purpose, corresponding lecture recordings were transcribed and made available to the Large Language Model GPT-4 as external knowledge source together with timestamps as metainformation by using RAG. The purpose of this is to prevent hallucinations and to enforce the use of the technical terms and phrases from the lecture. In an exercise platform developed to solve programming problems for an introductory programming lecture, students can request feedback on their solutions generated by GPT-4. For this task GPT-4 receives the students' code solution, the compiler output, the result of unit tests and the relevant passages from the lecture notes available through the use of RAG as additional context. The feedback generated by GPT-4 should guide students to solve problems independently and link to the lecture content, using the time stamps of the transcript as meta-information. In this way, the corresponding lecture videos can be viewed immediately at the corresponding positions. For the evaluation, students worked with the tool in a workshop and decided for each feedback whether it should be extended by RAG or not. First results based on a questionnaire and the collected usage data show that the use of RAG can improve feedback generation and is preferred by students in some situations. Due to the slower speed of feedback generation, the benefits are situation dependent.

The acquisition and performance of arithmetic skills and basic operations such as addition, subtraction, multiplication, and division are essential for daily functioning, and reflect complex cognitive processes. This paper explores the cognitive mechanisms powering arithmetic learning, presenting a neurobiologically plausible cognitive architecture that simulates the acquisition of these skills. I implement a number vectorization embedding network and an associative memory model to investigate how an intelligent system can learn and recall arithmetic equations in a manner analogous to the human brain. I perform experiments that provide insights into the generalization capabilities of connectionist models, neurological causes of dyscalculia, and the influence of network architecture on cognitive performance. Through this interdisciplinary investigation, I aim to contribute to ongoing research into the neural correlates of mathematical cognition in intelligent systems.

In this study, we investigated the effects of self-reflection in large language models (LLMs) on problem-solving performance. We instructed nine popular LLMs to answer a series of multiple-choice questions to provide a performance baseline. For each incorrectly answered question, we instructed eight types of self-reflecting LLM agents to reflect on their mistakes and provide themselves with guidance to improve problem-solving. Then, using this guidance, each self-reflecting agent attempted to re-answer the same questions. Our results indicate that LLM agents are able to significantly improve their problem-solving performance through self-reflection ($p < 0.001$). In addition, we compared the various types of self-reflection to determine their individual contribution to performance. All code and data are available on GitHub at https://github.com/matthewrenze/self-reflection

Vision-based robotic cloth unfolding has made great progress recently. However, prior works predominantly rely on value learning and have not fully explored policy-based techniques. Recently, the success of reinforcement learning on the large language model has shown that the policy gradient algorithm can enhance policy with huge action space. In this paper, we introduce ClothPPO, a framework that employs a policy gradient algorithm based on actor-critic architecture to enhance a pre-trained model with huge 10^6 action spaces aligned with observation in the task of unfolding clothes. To this end, we redefine the cloth manipulation problem as a partially observable Markov decision process. A supervised pre-training stage is employed to train a baseline model of our policy. In the second stage, the Proximal Policy Optimization (PPO) is utilized to guide the supervised model within the observation-aligned action space. By optimizing and updating the strategy, our proposed method increases the garment's surface area for cloth unfolding under the soft-body manipulation task. Experimental results show that our proposed framework can further improve the unfolding performance of other state-of-the-art methods.

This study introduces the continuous Educational Turkish Sign Language (E-TSL) dataset, collected from online Turkish language lessons for 5th, 6th, and 8th grades. The dataset comprises 1,410 videos totaling nearly 24 hours and includes performances from 11 signers. Turkish, an agglutinative language, poses unique challenges for sign language translation, particularly with a vocabulary where 64% are singleton words and 85% are rare words, appearing less than five times. We developed two baseline models to address these challenges: the Pose to Text Transformer (P2T-T) and the Graph Neural Network based Transformer (GNN-T) models. The GNN-T model achieved 19.13% BLEU-1 score and 3.28% BLEU-4 score, presenting a significant challenge compared to existing benchmarks. The P2T-T model, while demonstrating slightly lower performance in BLEU scores, achieved a higher ROUGE-L score of 22.09%. Additionally, we benchmarked our model using the well-known PHOENIX-Weather 2014T dataset to validate our approach.

Leveraging large language models for machine translation has demonstrated promising results. However, it does require the large language models to possess the capability of handling both the source and target languages in machine translation. When it is challenging to find large models that support the desired languages, resorting to continuous learning methods becomes a costly endeavor. To mitigate these expenses, we propose an innovative approach called RD (Relay Decoding), which entails concatenating two distinct large models that individually support the source and target languages. By incorporating a simple mapping layer to facilitate the connection between these two models and utilizing a limited amount of parallel data for training, we successfully achieve superior results in the machine translation task. Experimental results conducted on the Multi30k and WikiMatrix datasets validate the effectiveness of our proposed method.

Detecting stereotypes and biases in Large Language Models (LLMs) is crucial for enhancing fairness and reducing adverse impacts on individuals or groups when these models are applied. Traditional methods, which rely on embedding spaces or are based on probability metrics, fall short in revealing the nuanced and implicit biases present in various contexts. To address this challenge, we propose the FairMonitor framework and adopt a static-dynamic detection method for a comprehensive evaluation of stereotypes and biases in LLMs. The static component consists of a direct inquiry test, an implicit association test, and an unknown situation test, including 10,262 open-ended questions with 9 sensitive factors and 26 educational scenarios. And it is effective for evaluating both explicit and implicit biases. Moreover, we utilize the multi-agent system to construst the dynamic scenarios for detecting subtle biases in more complex and realistic setting. This component detects the biases based on the interaction behaviors of LLMs across 600 varied educational scenarios. The experimental results show that the cooperation of static and dynamic methods can detect more stereotypes and biased in LLMs.