Reinforcement learning (RL) is one of the active fields in machine learning, demonstrating remarkable potential in tackling real-world challenges. Despite its promising prospects, this methodology has encountered with issues and challenges, hindering it from achieving the best performance. In particular, these approaches lack decent performance when navigating environments and solving tasks with large observation space, often resulting in sample-inefficiency and prolonged learning times. This issue, commonly referred to as the curse of dimensionality, complicates decision-making for RL agents, necessitating a careful balance between attention and decision-making. RL agents, when augmented with human or large language models' (LLMs) feedback, may exhibit resilience and adaptability, leading to enhanced performance and accelerated learning. Such feedback, conveyed through various modalities or granularities including natural language, serves as a guide for RL agents, aiding them in discerning relevant environmental cues and optimizing decision-making processes. In this survey paper, we mainly focus on problems of two-folds: firstly, we focus on humans or an LLMs assistance, investigating the ways in which these entities may collaborate with the RL agent in order to foster optimal behavior and expedite learning; secondly, we delve into the research papers dedicated to addressing the intricacies of environments characterized by large observation space.

Confidence calibration in LLMs, i.e., aligning their self-assessed confidence with the actual accuracy of their responses, enabling them to self-evaluate the correctness of their outputs. However, current calibration methods for LLMs typically estimate two scalars to represent overall response confidence and correctness, which is inadequate for long-form generation where the response includes multiple atomic facts and may be partially confident and correct. These methods also overlook the relevance of each fact to the query. To address these challenges, we propose a Fact-Level Calibration framework that operates at a finer granularity, calibrating confidence to relevance-weighted correctness at the fact level. Furthermore, comprehensive analysis under the framework inspired the development of Confidence-Guided Fact-level Self-Correction ($\textbf{ConFix}$), which uses high-confidence facts within a response as additional knowledge to improve low-confidence ones. Extensive experiments across four datasets and six models demonstrate that ConFix effectively mitigates hallucinations without requiring external knowledge sources such as retrieval systems.

Accurate estimation of interaction forces is crucial for achieving fine, dexterous control in robotic systems. Although tactile sensor arrays offer rich sensing capabilities, their effective use has been limited by challenges such as calibration complexities, nonlinearities, and deformation. In this paper, we tackle these issues by presenting a novel method for obtaining 3D force estimation using tactile sensor arrays. Unlike existing approaches that focus on specific or decoupled force components, our method estimates full 3D interaction forces across an array of distributed sensors, providing comprehensive real-time feedback. Through systematic data collection and model training, our approach overcomes the limitations of prior methods, achieving accurate and reliable tactile-based force estimation. Besides, we integrate this estimation in a real-time control loop, enabling implicit, stable force regulation that is critical for precise robotic manipulation. Experimental validation on the Allegro robot hand with uSkin sensors demonstrates the effectiveness of our approach in real-time control, and its ability to enhance the robot's adaptability and dexterity.

Capturing fresh information in near real-time and using it to augment existing large language models (LLMs) is essential to generate up-to-date, grounded, and reliable output. This problem becomes particularly challenging when LLMs are used for informational tasks in rapidly evolving fields, such as Web search related to recent or unfolding events involving entities, where generating temporally relevant responses requires access to up-to-the-hour news sources. However, the information modeled by the parametric memory of LLMs is often outdated, and Web results from prototypical retrieval systems may fail to capture the latest relevant information and struggle to handle conflicting reports in evolving news. To address this challenge, we present the NEON framework, designed to extract emerging entity interactions -- such as events or activities -- as described in news articles. NEON constructs an entity-centric timestamped knowledge graph that captures such interactions, thereby facilitating enhanced QA capabilities related to news events. Our framework innovates by integrating open Information Extraction (openIE) style tuples into LLMs to enable in-context retrieval-augmented generation. This integration demonstrates substantial improvements in QA performance when tackling temporal, entity-centric search queries. Through NEON, LLMs can deliver more accurate, reliable, and up-to-date responses.

The combination of the Bayesian game and learning has a rich history, with the idea of controlling a single agent in a system composed of multiple agents with unknown behaviors given a set of types, each specifying a possible behavior for the other agents. The idea is to plan an agent's own actions with respect to those types which it believes are most likely to maximize the payoff. However, the type beliefs are often learned from past actions and likely to be incorrect. With this perspective in mind, we consider an agent in a game with type predictions of other components, and investigate the impact of incorrect beliefs to the agent's payoff. In particular, we formally define a tradeoff between risk and opportunity by comparing the payoff obtained against the optimal payoff, which is represented by a gap caused by trusting or distrusting the learned beliefs. Our main results characterize the tradeoff by establishing upper and lower bounds on the Pareto front for both normal-form and stochastic Bayesian games, with numerical results provided.

In recent years, Transformer-based models (Transformers) have achieved significant success in multivariate time series forecasting (MTSF). However, previous works focus on extracting features either from the time domain or the frequency domain, which inadequately captures the trends and periodic characteristics. To address this issue, we propose a wavelet learning framework to model complex temporal dependencies of the time series data. The wavelet domain integrates both time and frequency information, allowing for the analysis of local characteristics of signals at different scales. Additionally, the Softmax self-attention mechanism used by Transformers has quadratic complexity, which leads to excessive computational costs when capturing long-term dependencies. Therefore, we propose a novel attention mechanism: Rotary Route Attention (RoRA). Unlike Softmax attention, RoRA utilizes rotary position embeddings to inject relative positional information to sequence tokens and introduces a small number of routing tokens $r$ to aggregate information from the $KV$ matrices and redistribute it to the $Q$ matrix, offering linear complexity. We further propose WaveRoRA, which leverages RoRA to capture inter-series dependencies in the wavelet domain. We conduct extensive experiments on eight real-world datasets. The results indicate that WaveRoRA outperforms existing state-of-the-art models while maintaining lower computational costs. Our code is available at https://github.com/Leopold2333/WaveRoRA.

Accurate ocean forecasting systems are vital for understanding marine dynamics, which play a crucial role in environmental management and climate adaptation strategies. Traditional numerical solvers, while effective, are computationally expensive and time-consuming. Recent advancements in machine learning have revolutionized weather forecasting, offering fast and energy-efficient alternatives. Building on these advancements, we introduce SeaCast, a neural network designed for high-resolution, medium-range ocean forecasting. SeaCast employs a graph-based framework to effectively handle the complex geometry of ocean grids and integrates external forcing data tailored to the regional ocean context. Our approach is validated through experiments at a high spatial resolution using the operational numerical model of the Mediterranean Sea provided by the Copernicus Marine Service, along with both numerical and data-driven atmospheric forcings.

Due to the high cost of retraining from scratch, researchers attempt to employ machine unlearning to remove specific content from LLMs while preserving the overall performance. In this paper, we discuss several issues in machine unlearning for LLMs and provide our insights on possible approaches. To address the issue of inadequate evaluation of model outputs after unlearning, we introduce three additional metrics to evaluate token diversity, sentence semantics, and factual correctness. We then categorize unlearning methods into untargeted and targeted, and discuss their issues respectively. Specifically, the behavior that untargeted unlearning attempts to approximate is unpredictable and may involve hallucinations, and existing regularization is insufficient for targeted unlearning. To alleviate these issues, we propose using the objective of maximizing entropy (ME) for untargeted unlearning and incorporate answer preservation (AP) loss as regularization for targeted unlearning. Experimental results across three scenarios, i.e., fictitious unlearning, continual unlearning, and real-world unlearning, demonstrate the effectiveness of our approaches. In recent years, large language models (LLMs) have undergone rapid development, demonstrating impressive capabilities across a wide range of applications, from natural language processing to complex problem-solving. These concerns are particularly relevant within legal and regulatory frameworks, such as the Right to be Forgotten (Dang, 2021), which aims to empower individuals to have unauthorized data erased from digital records. Addressing these issues is crucial for ensuring the responsible deployment of LLMs in real-world applications. Due to the high cost of retraining LLMs, researchers have explored machine unlearning techniques, namely LLM unlearning (Cao & Yang, 2015; Bourtoule et al., 2021; Yao et al., 2023). The typical paradigm involves fine-tuning the target LLM on a specified set, known as the forget set, to obtain an unlearned model. As described in (Maini et al., 2024; Jin et al., 2024), the unlearned model should meet two primary goals: 1) it should not reveal any information contained in the forget set, and 2) it should maintain performance on the neighbor set, which has a distribution similar to the forget set but is not the target of unlearning, as well as on other tasks with general knowledge. While the first goal is generally easier to achieve, the main challenge lies in meeting the second goal (Liu et al., 2024b; Maini et al., 2024; Zhang et al., 2024a; Ji et al., 2024; Shi et al., 2024a; Wang et al., 2024c). In this paper, we have a closer look at machine unlearning for LLMs. We note that most prior studies (Maini et al., 2024; Ji et al., 2024; Jia et al., 2024; Jin et al., 2024; Shi et al., 2024a) primarily rely on ROUGE (Lin, 2004) as the sole metric for evaluating the output of unlearned models.

Urban air pollution hotspots pose significant health risks, yet their detection and analysis remain limited by the sparsity of public sensor networks. This paper addresses this challenge by combining predictive modeling and mechanistic approaches to comprehensively monitor pollution hotspots. We enhanced New Delhi's existing sensor network with 28 low-cost sensors, collecting PM2.5 data over 30 months from May 1, 2018, to Nov 1, 2020. Applying established definitions of hotspots to this data, we found the existence of additional 189 hidden hotspots apart from confirming 660 hotspots detected by the public network. Using predictive techniques like Space-Time Kriging, we identified hidden hotspots with 95% precision and 88% recall with 50% sensor failure rate, and with 98% precision and 95% recall with 50% missing sensors. The projected results of our predictive models were further compiled into policy recommendations for public authorities. Additionally, we developed a Gaussian Plume Dispersion Model to understand the mechanistic underpinnings of hotspot formation, incorporating an emissions inventory derived from local sources. Our mechanistic model is able to explain 65% of observed transient hotspots. Our findings underscore the importance of integrating data-driven predictive models with physics-based mechanistic models for scalable and robust air pollution management in resource-constrained settings.

Data breaches have begun to take on new dimensions and their prediction is becoming of great importance to organizations. Prior work has addressed this issue mainly from a technical perspective and neglected other interfering aspects such as the social media dimension. To fill this gap, we propose STRisk which is a predictive system where we expand the scope of the prediction task by bringing into play the social media dimension. We study over 3800 US organizations including both victim and non-victim organizations. For each organization, we design a profile composed of a variety of externally measured technical indicators and social factors. In addition, to account for unreported incidents, we consider the non-victim sample to be noisy and propose a noise correction approach to correct mislabeled organizations. We then build several machine learning models to predict whether an organization is exposed to experience a hacking breach. By exploiting both technical and social features, we achieve a Area Under Curve (AUC) score exceeding 98%, which is 12% higher than the AUC achieved using only technical features. Furthermore, our feature importance analysis reveals that open ports and expired certificates are the best technical predictors, while spreadability and agreeability are the best social predictors.