Reinforcement Learning (RL) has become a critical tool for optimization challenges within automation, leading to significant advancements in several areas. This review article examines the current landscape of RL within automation, with a particular focus on its roles in manufacturing, energy systems, and robotics. It discusses state-of-the-art methods, major challenges, and upcoming avenues of research within each sector, highlighting RL's capacity to solve intricate optimization challenges. The paper reviews the advantages and constraints of RL-driven optimization methods in automation. It points out prevalent challenges encountered in RL optimization, including issues related to sample efficiency and scalability; safety and robustness; interpretability and trustworthiness; transfer learning and meta-learning; and real-world deployment and integration. It further explores prospective strategies and future research pathways to navigate these challenges. Additionally, the survey includes a comprehensive list of relevant research papers, making it an indispensable guide for scholars and practitioners keen on exploring this domain.
The increasing complexity of natural disaster incidents demands innovative technological solutions to support first responders in their efforts. This paper introduces the TRIFFID system, a comprehensive technical framework that integrates unmanned ground and aerial vehicles with advanced artificial intelligence functionalities to enhance disaster response capabilities across wildfires, urban floods, and post-earthquake search and rescue missions. By leveraging state-of-the-art autonomous navigation, semantic perception, and human-robot interaction technologies, TRIFFID provides a sophisticated system composed of the following key components: hybrid robotic platform, centralized ground station, custom communication infrastructure, and smartphone application. The defined research and development activities demonstrate how deep neural networks, knowledge graphs, and multimodal information fusion can enable robots to autonomously navigate and analyze disaster environments, reducing personnel risks and accelerating response times. The proposed system enhances emergency response teams by providing advanced mission planning, safety monitoring, and adaptive task execution capabilities. Moreover, it ensures real-time situational awareness and operational support in complex and risky situations, facilitating rapid and precise information collection and coordinated actions.
Diagnosing diseases through histopathology whole slide images (WSIs) is fundamental in modern pathology but is challenged by the gigapixel scale and complexity of WSIs. Trained histopathologists overcome this challenge by navigating the WSI, looking for relevant patches, taking notes, and compiling them to produce a final holistic diagnostic. Traditional AI approaches, such as multiple instance learning and transformer-based models, fail short of such a holistic, iterative, multi-scale diagnostic procedure, limiting their adoption in the real-world. We introduce PathFinder, a multi-modal, multi-agent framework that emulates the decision-making process of expert pathologists. PathFinder integrates four AI agents, the Triage Agent, Navigation Agent, Description Agent, and Diagnosis Agent, that collaboratively navigate WSIs, gather evidence, and provide comprehensive diagnoses with natural language explanations. The Triage Agent classifies the WSI as benign or risky; if risky, the Navigation and Description Agents iteratively focus on significant regions, generating importance maps and descriptive insights of sampled patches. Finally, the Diagnosis Agent synthesizes the findings to determine the patient's diagnostic classification. Our Experiments show that PathFinder outperforms state-of-the-art methods in skin melanoma diagnosis by 8% while offering inherent explainability through natural language descriptions of diagnostically relevant patches. Qualitative analysis by pathologists shows that the Description Agent's outputs are of high quality and comparable to GPT-4o. PathFinder is also the first AI-based system to surpass the average performance of pathologists in this challenging melanoma classification task by 9%, setting a new record for efficient, accurate, and interpretable AI-assisted diagnostics in pathology. Data, code and models available at https://pathfinder-dx.github.io/
Generative tasks about molecules, including but not limited to molecule generation, are crucial for drug discovery and material design, and have consistently attracted significant attention. In recent years, diffusion models have emerged as an impressive class of deep generative models, sparking extensive research and leading to numerous studies on their application to molecular generative tasks. Despite the proliferation of related work, there remains a notable lack of up-to-date and systematic surveys in this area. Particularly, due to the diversity of diffusion model formulations, molecular data modalities, and generative task types, the research landscape is challenging to navigate, hindering understanding and limiting the area's growth. To address this, this paper conducts a comprehensive survey of diffusion model-based molecular generative methods. We systematically review the research from the perspectives of methodological formulations, data modalities, and task types, offering a novel taxonomy. This survey aims to facilitate understanding and further flourishing development in this area. The relevant papers are summarized at: https://github.com/AzureLeon1/awesome-molecular-diffusion-models.
Despite recent advances, sampling-based inference for Bayesian Neural Networks (BNNs) remains a significant challenge in probabilistic deep learning. While sampling-based approaches do not require a variational distribution assumption, current state-of-the-art samplers still struggle to navigate the complex and highly multimodal posteriors of BNNs. As a consequence, sampling still requires considerably longer inference times than non-Bayesian methods even for small neural networks, despite recent advances in making software implementations more efficient. Besides the difficulty of finding high-probability regions, the time until samplers provide sufficient exploration of these areas remains unpredictable. To tackle these challenges, we introduce an ensembling approach that leverages strategies from optimization and a recently proposed sampler called Microcanonical Langevin Monte Carlo (MCLMC) for efficient, robust and predictable sampling performance. Compared to approaches based on the state-of-the-art No-U-Turn Sampler, our approach delivers substantial speedups up to an order of magnitude, while maintaining or improving predictive performance and uncertainty quantification across diverse tasks and data modalities. The suggested Microcanonical Langevin Ensembles and modifications to MCLMC additionally enhance the method's predictability in resource requirements, facilitating easier parallelization. All in all, the proposed method offers a promising direction for practical, scalable inference for BNNs.
Despite their remarkable capabilities, large language models often struggle with tasks requiring complex reasoning and planning. While existing approaches like Chain-of-Thought prompting and tree search techniques show promise, they are limited by their reliance on predefined heuristics and computationally expensive exploration strategies. We propose Policy-Guided Tree Search (PGTS), a framework that combines reinforcement learning with structured tree exploration to efficiently navigate reasoning paths. Our key innovation is a learned policy that dynamically decides between expanding, branching, backtracking, or terminating exploration, eliminating the need for manual heuristics or exhaustive search. Experiments across mathematical reasoning, logical deduction, and planning benchmarks demonstrate that PGTS achieves superior reasoning performance while significantly reducing computational costs compared to existing methods. These results establish PGTS as a scalable and effective solution for tackling complex reasoning tasks with LLMs.
As AI models grow in power and generality, understanding how agents learn and make decisions in complex environments is critical to promoting ethical behavior. This study introduces the Odyssey, a lightweight, adaptive text based adventure game, providing a scalable framework for exploring AI ethics and safety. The Odyssey examines the ethical implications of implementing biological drives, specifically, self preservation, into three different agents. A Bayesian agent optimized with NEAT, a Bayesian agent optimized with stochastic variational inference, and a GPT 4o agent. The agents select actions at each scenario to survive, adapting to increasingly challenging scenarios. Post simulation analysis evaluates the ethical scores of the agent decisions, uncovering the tradeoffs it navigates to survive. Specifically, analysis finds that when danger increases, agents ethical behavior becomes unpredictable. Surprisingly, the GPT 4o agent outperformed the Bayesian models in both survival and ethical consistency, challenging assumptions about traditional probabilistic methods and raising a new challenge to understand the mechanisms of LLMs' probabilistic reasoning.
Large Language Models have proved surprisingly effective at solving a wide range of tasks from just a handful of examples. However, their lack of reliability and modularity limits their capacity to tackle large problems that require many steps of reasoning. In response, researchers have proposed advanced pipelines that leverage domain-specific knowledge to chain smaller prompts, provide intermediate feedback and improve performance through search. However, the current complexity of writing, tuning, maintaining and improving such pipelines has limited their sophistication. We propose oracular programming, a foundational paradigm for building LLM-enabled applications that lets domain experts express high-level problem-solving strategies as programs with unresolved choice points. These choice points are resolved at runtime by LLMs, which generalize from user-provided examples of correct and incorrect decisions. An oracular program is composed of three orthogonal components: a strategy that consists in a nondeterministic program with choice points that can be reified into a search tree, a policy that specifies how to navigate this tree with the help of LLM oracles, and a set of demonstrations that describe successful and unsuccessful search tree navigation scenarios across diverse problem instances. Each component is expressed in a dedicated programming language and can be independently improved or substituted. We address the key programming language design challenges of modularly composing oracular programs and enforcing consistency between their components as they evolve.
While high-resolution microscopic techniques are crucial for studying cellular structures in cell biology, obtaining such images from thick 3D engineered tissues remains challenging. In this review, we explore advancements in fluorescence microscopy, alongside the use of various fluorescent probes and material processing techniques to address these challenges. We navigate through the diverse array of imaging options available in tissue engineering field, from wide field to super-resolution microscopy, so researchers can make more informed decisions based on the specific tissue and cellular structures of interest. Finally, we provide some recent examples of how traditional limitations on obtaining high-resolution images on sub-cellular architecture within 3D tissues have been overcome by combining imaging advancements with innovative tissue engineering approaches.
Public policy shapes the economic landscape, influencing everything from corporate behavior to individual investment decisions. For Environmental, Social, and Governance (ESG) investors, these policy shifts can create opportunities and challenges as they navigate an ever-changing regulatory environment. The contrast between the Trump and Biden administrations offers a striking example of how differing political agendas can affect ESG investments. Trump's first term was marked by deregulation and policies favoring fossil fuels, which created an uncertain environment for sustainable investments. When Biden assumed office, his focus on climate action and clean energy reinvigorated the ESG sector, offering a more stable and supportive landscape for green investments. However, with Trump's return to power in his second term, these policies are being reversed again, leading to further volatility. This paper explores how such dramatic shifts in public policy influence economic strategies and directly impact ESG investors' decisions, forcing them to constantly reassess their portfolios in response to changing political climates.
We address path-planning for a mobile agent to navigate in an unknown environment with minimum exposure to a spatially and temporally varying threat field. The threat field is estimated using pointwise noisy measurements from a mobile sensor network. For this problem, we present a new information gain measure for optimal sensor placement that quantifies reduction in uncertainty in the path cost rather than the environment state. This measure, which we call the context-relevant mutual information (CRMI), couples the sensor placement and path-planning problem. We propose an iterative coupled sensor configuration and path-planning (CSCP) algorithm. At each iteration, this algorithm places sensors to maximize CRMI, updates the threat estimate using new measurements, and recalculates the path with minimum expected exposure to the threat. The iterations converge when the path cost variance, which is an indicator of risk, reduces below a desired threshold. We show that CRMI is submodular, and therefore, greedy optimization provides near-optimal sensor placements while maintaining computational efficiency of the CSCP algorithm. Distance-based sensor reconfiguration costs are introduced in a modified CRMI measure, which we also show to be submodular. Through numerical simulations, we demonstrate that the principal advantage of this algorithm is that near-optimal low-variance paths are achieved using far fewer sensor measurements as compared to a standard sensor placement method.
We explore a suite of generative modelling techniques to efficiently navigate and explore the complex landscapes of odor and the broader chemical space. Unlike traditional approaches, we not only generate molecules but also predict the odor likeliness with ROC AUC score of 0.97 and assign probable odor labels. We correlate odor likeliness with physicochemical features of molecules using machine learning techniques and leverage SHAP (SHapley Additive exPlanations) to demonstrate the interpretability of the function. The whole process involves four key stages: molecule generation, stringent sanitization checks for molecular validity, fragrance likeliness screening and odor prediction of the generated molecules. By making our code and trained models publicly accessible, we aim to facilitate broader adoption of our research across applications in fragrance discovery and olfactory research.
When designing materials to optimize certain properties, there are often many possible configurations of designs that need to be explored. For example, the materials' composition of elements will affect properties such as strength or conductivity, which are necessary to know when developing new materials. Exploring all combinations of elements to find optimal materials becomes very time consuming, especially when there are more design variables. For this reason, there is growing interest in using machine learning (ML) to predict a material's properties. In this work, we model the optimization of certain material properties as a tensor completion problem, to leverage the structure of our datasets and navigate the vast number of combinations of material configurations. Across a variety of material property prediction tasks, our experiments show tensor completion methods achieving 10-20% decreased error compared with baseline ML models such as GradientBoosting and Multilayer Perceptron (MLP), while maintaining similar training speed.
We would like a robot to navigate to a goal location while minimizing state uncertainty. To aid the robot in this endeavor, maps provide a prior belief over the location of objects and regions of interest. To localize itself within the map, a robot identifies mapped landmarks using its sensors. However, as the time between map creation and robot deployment increases, portions of the map can become stale, and landmarks, once believed to be permanent, may disappear. We refer to the propensity of a landmark to disappear as landmark evanescence. Reasoning about landmark evanescence during path planning, and the associated impact on localization accuracy, requires analyzing the presence or absence of each landmark, leading to an exponential number of possible outcomes of a given motion plan. To address this complexity, we develop BRULE, an extension of the Belief Roadmap. During planning, we replace the belief over future robot poses with a Gaussian mixture which is able to capture the effects of landmark evanescence. Furthermore, we show that belief updates can be made efficient, and that maintaining a random subset of mixture components is sufficient to find high quality solutions. We demonstrate performance in simulated and real-world experiments. Software is available at https://bit.ly/BRULE.
This paper describes the architecture of our system developed for Task 3 of SemEval-2024: Multimodal Emotion-Cause Analysis in Conversations. Our project targets the challenges of subtask 2, dedicated to Multimodal Emotion-Cause Pair Extraction with Emotion Category (MECPE-Cat), and constructs a dual-component system tailored to the unique challenges of this task. We divide the task into two subtasks: emotion recognition in conversation (ERC) and emotion-cause pair extraction (ECPE). To address these subtasks, we capitalize on the abilities of Large Language Models (LLMs), which have consistently demonstrated state-of-the-art performance across various natural language processing tasks and domains. Most importantly, we design an approach of emotion-cause-aware instruction-tuning for LLMs, to enhance the perception of the emotions with their corresponding causal rationales. Our method enables us to adeptly navigate the complexities of MECPE-Cat, achieving a weighted average 34.71% F1 score of the task, and securing the 2nd rank on the leaderboard. The code and metadata to reproduce our experiments are all made publicly available.
Reinforcement learning (RL) agents often face challenges in balancing exploration and exploitation, particularly in environments where sparse or dense rewards bias learning. Biological systems, such as human toddlers, naturally navigate this balance by transitioning from free exploration with sparse rewards to goal-directed behavior guided by increasingly dense rewards. Inspired by this natural progression, we investigate the Toddler-Inspired Reward Transition in goal-oriented RL tasks. Our study focuses on transitioning from sparse to potential-based dense (S2D) rewards while preserving optimal strategies. Through experiments on dynamic robotic arm manipulation and egocentric 3D navigation tasks, we demonstrate that effective S2D reward transitions significantly enhance learning performance and sample efficiency. Additionally, using a Cross-Density Visualizer, we show that S2D transitions smooth the policy loss landscape, resulting in wider minima that improve generalization in RL models. In addition, we reinterpret Tolman's maze experiments, underscoring the critical role of early free exploratory learning in the context of S2D rewards.
Understanding the traversability of terrain is essential for autonomous robot navigation, particularly in unstructured environments such as natural landscapes. Although traditional methods, such as occupancy mapping, provide a basic framework, they often fail to account for the complex mobility capabilities of some platforms such as legged robots. In this work, we propose a method for estimating terrain traversability by learning from demonstrations of human walking. Our approach leverages dense, pixel-wise feature embeddings generated using the DINOv2 vision Transformer model, which are processed through an encoder-decoder MLP architecture to analyze terrain segments. The averaged feature vectors, extracted from the masked regions of interest, are used to train the model in a reconstruction-based framework. By minimizing reconstruction loss, the network distinguishes between familiar terrain with a low reconstruction error and unfamiliar or hazardous terrain with a higher reconstruction error. This approach facilitates the detection of anomalies, allowing a legged robot to navigate more effectively through challenging terrain. We run real-world experiments on the ANYmal legged robot both indoor and outdoor to prove our proposed method. The code is open-source, while video demonstrations can be found on our website: https://rpl-cs-ucl.github.io/STEPP
This study introduces the LPBSA, an advanced optimization algorithm that combines Learner Performance-based Behavior (LPB) and Simulated Annealing (SA) in a hybrid approach. Emphasizing metaheuristics, the LPBSA addresses and mitigates the challenges associated with traditional LPB methodologies, enhancing convergence, robustness, and adaptability in solving complex optimization problems. Through extensive evaluations using benchmark test functions, the LPBSA demonstrates superior performance compared to LPB and competes favorably with established algorithms such as PSO, FDO, LEO, and GA. Real-world applications underscore the algorithm's promise, with LPBSA outperforming the LEO algorithm in two tested scenarios. Based on the study results many test function results such as TF5 by recording (4.76762333) and some other test functions provided in the result section prove that LPBSA outperforms popular algorithms. This research highlights the efficacy of a hybrid approach in the ongoing evolution of optimization algorithms, showcasing the LPBSA's capacity to navigate diverse optimization landscapes and contribute significantly to addressing intricate optimization challenges.
Artificial intelligence is reshaping creative domains, yet its co-creative processes, especially in group settings with novice users, remain under explored. To bridge this gap, we conducted a case study in a college-level course where nine undergraduate students were tasked with creating three original music tracks using AI tools over 10 weeks. The study spanned the entire creative journey from ideation to releasing these songs on Spotify. Participants leveraged AI for music and lyric production, cover art, and distribution. Our findings highlight how AI transforms creative workflows: accelerating ideation but compressing the traditional preparation stage, and requiring novices to navigate a challenging idea selection and validation phase. We also identified a new "collaging and refinement" stage, where participants creatively combined diverse AI-generated outputs into cohesive works. Furthermore, AI influenced group social dynamics and role division among human creators. Based on these insights, we propose the Human-AI Co-Creation Stage Model and the Human-AI Agency Model, offering new perspectives on collaborative co-creation with AI.
Multi-task model merging offers an efficient solution for integrating knowledge from multiple fine-tuned models, mitigating the significant computational and storage demands associated with multi-task training. As a key technique in this field, Task Arithmetic (TA) defines task vectors by subtracting the pre-trained model ($\theta_{\text{pre}}$) from the fine-tuned task models in parameter space, then adjusting the weight between these task vectors and $\theta_{\text{pre}}$ to balance task-generalized and task-specific knowledge. Despite the promising performance of TA, conflicts can arise among the task vectors, particularly when different tasks require distinct model adaptations. In this paper, we formally define this issue as knowledge conflicts, characterized by the performance degradation of one task after merging with a model fine-tuned for another task. Through in-depth analysis, we show that these conflicts stem primarily from the components of task vectors that align with the gradient of task-specific losses at $\theta_{\text{pre}}$. To address this, we propose Task Arithmetic in Trust Region (TATR), which defines the trust region as dimensions in the model parameter space that cause only small changes (corresponding to the task vector components with gradient orthogonal direction) in the task-specific losses. Restricting parameter merging within this trust region, TATR can effectively alleviate knowledge conflicts. Moreover, TATR serves as both an independent approach and a plug-and-play module compatible with a wide range of TA-based methods. Extensive empirical evaluations on eight distinct datasets robustly demonstrate that TATR improves the multi-task performance of several TA-based model merging methods by an observable margin.