23 papers · ranked by Valyu relevance
Andrea Scorsoglio, Roberto Furfaro
In this paper VisualEnv, a new tool for creating visual environment for reinforcement learning is introduced. It is the product of an integration of an open-source modelling and rendering software, Blender, and a python module used to generate environment model for simulation, OpenAI Gym. VisualEnv allows the user to…
Yingjie Zhu, Wan Zuha Wan Hasan, Hafiz Rashidi Harun Ramli, Nor Mohd Haziq Norsahperi + 5 more
Deep reinforcement learning (DRL), a vital branch of artificial intelligence, has shown great promise in mobile robot navigation within dynamic environments. However, existing studies mainly focus on simplified dynamic scenarios or the modeling of static environments, which results in trained models lacking sufficient…
Tingfeng Hui, Hao Xu, Pengyu Zhu, Hongsheng Xin + 4 more
Large language models (LLMs) deployed in real-world agentic applications must be capable of replanning and adapting when mid-task disruptions invalidate their prior decisions. Existing dynamic benchmarks primarily measure whether LLMs can detect temporal changes in a timely manner, leaving the complementary challenge…
Roberto Gallotta, Antonios Liapis, Georgios N. Yannakakis
Evolutionary search via the quality-diversity (QD) paradigm can discover highly performing solutions in different behavioural niches, showing considerable potential in complex real-world scenarios such as evolutionary robotics. Yet most QD methods only tackle static tasks that are fixed over time, which is rarely the…
Jiachun Li, Zhuoran Jin, Tianyi Men, Yupu Hao + 11 more
Environments serve as interactive systems for large language model (LLM) based agents across diverse scenarios and play a crucial role in driving the continual evolution of model capabilities. Despite this importance, existing work lacks a systematic categorization and deep analysis. This paper systematically studies…
Anusha Alexander, V. N. Suchir Vangaveeti, Kalaichelvi Venkatesan, Jinane Mounsef + 1 more
Mobile robots have emerged as a reliable solution for dynamic navigation in real-world applications. Effective deployment in high-density crowds and emergency scenarios requires not only accurate path planning but also rapid adaptation to changing environments. However, autonomous navigation in such environments…
T Dvorakova, V Lobellova, P Manubens-Coda, A Sanchez-Jimenez + 3 more
Animals and humans receive the most critical information from parts of the environment that are immediately inaccessible, possibly only visually explored, and highly dynamic. The brain must effectively process potential interactions between elements in such an environment to make appropriate decisions in critical…
Avaneesh V. Narla, Terence Hwa, Arvind Murugan
Microbial ecosystems are commonly modeled by fixed interactions between species in steady exponential growth states. However, microbes often modify their environments so strongly that they are forced out of the exponential state into stressed or non-growing states. Such dynamics are typical of ecological succession in…
JiHun Kim, Jee Hang Lee
Introduction Recent advances in computational neuroscience highlight the significance of prefrontal cortical meta-control mechanisms in facilitating flexible and adaptive human behavior. In addition, hippocampal function, particularly mental simulation capacity, proves essential in this adaptive process. Rooted from…
Yongxing Sun, Jianing Gao, Jiarong Li, Yanqiong Chen
Sustainable tourism is widely advocated as a low-impact development strategy that promotes economic growth while preserving ecological integrity. However, empirical evidence increasingly reveals complex environmental trade-offs associated with tourism expansion, particularly in ecologically sensitive heritage sites.…
Akash K. Rao, Sushil Chandra, Varun Dutt
Dynamic decision-making involves a series of interconnected interdependent confluence of decisions to be made. Experiential training is preferred over traditional methods to train individuals in dynamic decision-making. Imparting experiential training in physical settings can be very expensive and unreliable. In…
Zhang, Jiayi, Peng, Yiran + 26 more
Humans naturally adapt to diverse environments by learning underlying rules across worlds with different dynamics, observations, and reward structures. In contrast, existing agents typically demonstrate improvements via self-evolving within a single domain, implicitly assuming a fixed environment distribution.…
Noah Cohen Kalafut, Chenfeng He, Jie Sheng, Pramod Bharadwaj Chandrashekar + 2 more
Single cells interact continuously to form a cell environment that drives key biological processes. Cells and cell environments are highly dynamic across time and space, fundamentally governed by molecular mechanisms, such as gene expression. Recent sequencing techniques measure single-cell-level gene expression under…
Xingkun Yin, Hongyang Du
Most existing memory-enhanced Large Language Model (LLM) approaches implicitly assume that memory validity can be established either through external evaluators that provide task-specific success signals or through internal model cognition, such as reflection, for editing memory entries. However, these assumptions…
Hyun-Seob Song, Na-Rae Lee, Aimee K. Kessell, Hugh C. McCullough + 3 more
Microbial communities in nature are dynamically evolving as member species change their interactions subject to environmental variations. Accounting for such context-dependent dynamic variations in interspecies interactions is critical for predictive ecological modeling. In the absence of generalizable theoretical…
YuHan Wei, ChangWook Lee, SeokWon Han, Anna Kim
Introduction This research aims to address the challenges in model construction for the Extended Mind for the Design of the Human Environment. Specifically, we employ the ResNet-50, LSTM, and Object Tracking Algorithms approaches to achieve collaborative construction of high-quality virtual assets, image optimization…
Jaeeon Lee, Jay A. Hennig, Vanessa Frelih, Samuel J. Gershman + 1 more
Value computation is fundamental to the survival of animals. Classical models suggest value is stored in synaptic weight through plasticity whereas more recent theories propose that recurrent network dynamics can encode and update value independently of synaptic change. Although these two mechanisms are not mutually…
David Mansfield, Allahyar Montazeri
The environmental pollution caused by various sources has escalated the climate crisis making the need to establish reliable, intelligent, and persistent environmental monitoring solutions more crucial than ever. Mobile sensing systems are a popular platform due to their cost-effectiveness and adaptability. However, in…
Authors not listed
Machine olfaction—the artificial replication of the sense of smell—faces significant challenges due to the absence of large, standardized training datasets. Unlike vision, language, and audio models, which benefit from extensive corpora such as ImageNet, GLUE, and AudioSet, olfaction lacks scaled equivalents and…
Konstantinos Voudouris, Ben Slater, Lucy G. Cheke, Wout Schellaert + 10 more
'José Hernández-Orallo' 'Marta Halina' 'Matishalin Patel' 'Ibrahim Alhas' 'Matteo G. Mecattaf' 'John Burden' 'Joel Holmes' 'Niharika Chaubey' 'Niall Donnelly' 'Matthew Crosby'] The Animal-AI Environment is a unique game-based research platform designed to facilitate collaboration between the artificial intelligence and…
Amit Kahana, Lior Segev, Doron Lancet
The origin of life must have involved an unlikely transition from chaotic chemistry to reproducing supramolecular structures. Previous quantitative analyses of reproducing mutually catalytic networks made of simple molecules have led to increasing popularity of this pre-RNA scenario for life’s origin. Here, we…
Authors not listed
Deriving versatile and robust mechanistic models from experimental data is a key challenge in engineering and natural sciences. This is especially true in chemical reaction engineering, where reactor manufacturers and operators increasingly pursue the development and maintenance of digital twins that rely on frequent…
Laihao Liu, Tiankai Chen, Zhongxin Chen
The dynamic response of single atom catalysts to a reactive environment is an increasingly significant topic for understanding the reaction mechanism at the molecular level. In particular, single atoms may experience dynamic aggregation into clusters or nanoparticles driven by thermodynamic and kinetic factors. Herein…