The aim of inverse reinforcement learning (IRL) is to infer an agent's preferences from observing their behaviour. Usually, preferences are modelled as a reward function, $R$, and behaviour is modelled as a policy, $\pi$. One of the central difficulties in IRL is that multiple preferences may lead to the same observed behaviour. That is, $R$ is typically underdetermined by $\pi$, which means that $R$ is only partially identifiable. Recent work has characterised the extent of this partial identifiability for different types of agents, including optimal and Boltzmann-rational agents. However, work so far has only considered agents that discount future reward exponentially: this is a serious limitation, especially given that extensive work in the behavioural sciences suggests that humans are better modelled as discounting hyperbolically. In this work, we newly characterise partial identifiability in IRL for agents with non-exponential discounting: our results are in particular relevant for hyperbolical discounting, but they also more generally apply to agents that use other types of (non-exponential) discounting. We significantly show that generally IRL is unable to infer enough information about $R$ to identify the correct optimal policy, which entails that IRL alone can be insufficient to adequately characterise the preferences of such agents.

The current Adaptive Cruise Control (ACC) systems are vulnerable to "road bully" such as cut-ins. This paper proposed an Anti-bullying Adaptive Cruise Control (AACC) approach with proactive right-of-way protection ability. It bears the following features: i) with the enhanced capability of preventing bullying from cut-ins; ii) optimal but not unsafe; iii) adaptive to various driving styles of cut-in vehicles; iv) with real-time field implementation capability. The proposed approach can identify other road users' driving styles online and conduct game-based motion planning for right-of-way protection. A detailed investigation of the simulation results shows that the proposed approach can prevent bullying from cut-ins and be adaptive to different cut-in vehicles' driving styles. The proposed approach is capable of enhancing travel efficiency by up to 29.55% under different cut-in gaps and can strengthen driving safety compared with the current ACC controller. The proposed approach is flexible and robust against traffic congestion levels. It can improve mobility by up to 11.93% and robustness by 8.74% in traffic flow. Furthermore, the proposed approach can support real-time field implementation by ensuring less than 50 milliseconds computation time.

The field of autonomous web navigation has seen significant advancements, driven by the capabilities of Large Language Models (LLMs) in both mobile and webpage interactions [Wang et al., 2024a, Mialon et al., 2023, Xi et al., 2023]. Preliminary attempts, such as the ChatGPT Plugin [OpenAI, 2023], have also started building practical applications of web knowledge-based chatbot. Web navigation can be described as processes where agents perform specific tasks on behalf of human users within a web environment, involving the interpretation of high-level user instructions, decomposing them into basic operations, and interacting with complex web pages dynamically. To achieve this, agents must understand intricate web scenarios, adapt to dynamic changes such as noisy text and evolving HTML structures, and generalize successful operations to unseen tasks, thus freeing humans from repetitive interactions with computer interfaces. Traditional web agents trained through reinforcement learning [Shi et al., 2017, Yao et al., 2022] often mimic human behavior using predefined actions like typing, searching, and navigating to a specific page.

Abstract: Timely detection and geolocation of events based on social data can provide critical information for applications such as crisis response and resource allocation. However, most existing methods are greatly affected by event detection errors, leading to insufficient geolocation accuracy. To this end, this paper proposes a novel end-to-end event geolocation method (GTOP) leveraging Hyperbolic space and toponym hierarchies. Specifically, the proposed method contains one event detection module and one geolocation module. The event detection module constructs a heterogeneous information networks based on social data, and then constructs a homogeneous message graph and combines it with the text and time feature of the message to learning initial features of nodes. Node features are updated in Hyperbolic space and then fed into a classifier for event detection. To reduce the geolocation error, this paper proposes a noise toponym filtering algorithm (HIST) based on the hierarchical structure of toponyms. HIST analyzes the hierarchical structure of toponyms mentioned in the event cluster, taking the highly frequent city-level locations as the coarsegrained locations for events. To further improve the geolocation accuracy, we propose a fine-grained pseudo toponyms generation algorithm (FIT) based on the output of HIST, and combine generated pseudo toponyms with filtered toponyms to locate events based on the geographic center points of the combined toponyms. Extensive experiments are conducted on the Chinese dataset constructed in this paper and another public English dataset. The experimental results show that the proposed method is superior to the state-of-the-art baselines.

Markov decision processes (MDP) are a well-established model for sequential decision-making in the presence of probabilities. In robust MDP (RMDP), every action is associated with an uncertainty set of probability distributions, modelling that transition probabilities are not known precisely. Based on the known theoretical connection to stochastic games, we provide a framework for solving RMDPs that is generic, reliable, and efficient. It is *generic* both with respect to the model, allowing for a wide range of uncertainty sets, including but not limited to intervals, $L^1$- or $L^2$-balls, and polytopes; and with respect to the objective, including long-run average reward, undiscounted total reward, and stochastic shortest path. It is *reliable*, as our approach not only converges in the limit, but provides precision guarantees at any time during the computation. It is *efficient* because -- in contrast to state-of-the-art approaches -- it avoids explicitly constructing the underlying stochastic game. Consequently, our prototype implementation outperforms existing tools by several orders of magnitude and can solve RMDPs with a million states in under a minute.

We present a case for the use of Reinforcement Learning (RL) for the design of physics instrument as an alternative to gradient-based instrument-optimization methods. It's applicability is demonstrated using two empirical studies. One is longitudinal segmentation of calorimeters and the second is both transverse segmentation as well longitudinal placement of trackers in a spectrometer. Based on these experiments, we propose an alternative approach that offers unique advantages over differentiable programming and surrogate-based differentiable design optimization methods. First, Reinforcement Learning (RL) algorithms possess inherent exploratory capabilities, which help mitigate the risk of convergence to local optima. Second, this approach eliminates the necessity of constraining the design to a predefined detector model with fixed parameters. Instead, it allows for the flexible placement of a variable number of detector components and facilitates discrete decision-making. We then discuss the road map of how this idea can be extended into designing very complex instruments. The presented study sets the stage for a novel framework in physics instrument design, offering a scalable and efficient framework that can be pivotal for future projects such as the Future Circular Collider (FCC), where most optimized detectors are essential for exploring physics at unprecedented energy scales.

The intersection of technology and mental health has spurred innovative approaches to assessing emotional well-being, particularly through computational techniques applied to audio data analysis. This study explores the application of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) models on wavelet extracted features and Mel-frequency Cepstral Coefficients (MFCCs) for emotion detection from spoken speech. Data augmentation techniques, feature extraction, normalization, and model training were conducted to evaluate the models' performance in classifying emotional states. Results indicate that the CNN model achieved a higher accuracy of 61% compared to the LSTM model's accuracy of 56%. Both models demonstrated better performance in predicting specific emotions such as surprise and anger, leveraging distinct audio features like pitch and speed variations. Recommendations include further exploration of advanced data augmentation techniques, combined feature extraction methods, and the integration of linguistic analysis with speech characteristics for improved accuracy in mental health diagnostics. Collaboration for standardized dataset collection and sharing is recommended to foster advancements in affective computing and mental health care interventions. NTRODUCTION In recent years, the intersection of technology and mental health has opened up new avenues for assessing and understanding emotional well-being, with a particular focus on leveraging computational techniques for analyzing spoken speech.

The research of machine learning (ML) algorithms for human activity recognition (HAR) has made significant progress with publicly available datasets. However, most research prioritizes statistical metrics over examining negative sample details. While recent models like transformers have been applied to HAR datasets with limited success from the benchmark metrics, their counterparts have effectively solved problems on similar levels with near 100% accuracy. This raises questions about the limitations of current approaches. This paper aims to address these open questions by conducting a fine-grained inspection of six popular HAR benchmark datasets. We identified for some parts of the data, none of the six chosen state-of-the-art ML methods can correctly classify, denoted as the intersect of false classifications (IFC). Analysis of the IFC reveals several underlying problems, including ambiguous annotations, irregularities during recording execution, and misaligned transition periods. We contribute to the field by quantifying and characterizing annotated data ambiguities, providing a trinary categorization mask for dataset patching, and stressing potential improvements for future data collections.

Robot decision-making in partially observable, real-time, dynamic, and multi-agent environments remains a difficult and unsolved challenge. Model-free reinforcement learning (RL) is a promising approach to learning decision-making in such domains, however, end-to-end RL in complex environments is often intractable. To address this challenge in the RoboCup Standard Platform League (SPL) domain, we developed a novel architecture integrating RL within a classical robotics stack, while employing a multi-fidelity sim2real approach and decomposing behavior into learned sub-behaviors with heuristic selection. Our architecture led to victory in the 2024 RoboCup SPL Challenge Shield Division. In this work, we fully describe our system's architecture and empirically analyze key design decisions that contributed to its success. Our approach demonstrates how RL-based behaviors can be integrated into complete robot behavior architectures.

We aim to develop a model-based planning framework for world models that can be scaled with increasing model and data budgets for general-purpose manipulation tasks with only language and vision inputs. To this end, we present FLow-centric generative Planning (FLIP), a model-based planning algorithm on visual space that features three key modules: 1. a multi-modal flow generation model as the general-purpose action proposal module; 2. a flow-conditioned video generation model as the dynamics module; and 3. a vision-language representation learning model as the value module. Given an initial image and language instruction as the goal, FLIP can progressively search for long-horizon flow and video plans that maximize the discounted return to accomplish the task. FLIP is able to synthesize long-horizon plans across objects, robots, and tasks with image flows as the general action representation, and the dense flow information also provides rich guidance for long-horizon video generation. In addition, the synthesized flow and video plans can guide the training of low-level control policies for robot execution. Experiments on diverse benchmarks demonstrate that FLIP can improve both the success rates and quality of long-horizon video plan synthesis and has the interactive world model property, opening up wider applications for future works.