Soft Actor-Critic (SAC) has achieved notable success in continuous control tasks but struggles in sparse reward settings, where infrequent rewards make efficient exploration challenging. While novelty-based exploration methods address this issue by encouraging the agent to explore novel states, they are not trivial to apply to SAC. In particular, managing the interaction between novelty-based exploration and SAC's stochastic policy can lead to inefficient exploration and redundant sample collection. In this paper, we propose KEA (Keeping Exploration Alive) which tackles the inefficiencies in balancing exploration strategies when combining SAC with novelty-based exploration. KEA integrates a novelty-augmented SAC with a standard SAC agent, proactively coordinated via a switching mechanism. This coordination allows the agent to maintain stochasticity in high-novelty regions, enhancing exploration efficiency and reducing repeated sample collection. We first analyze this potential issue in a 2D navigation task, and then evaluate KEA on the DeepSea hard-exploration benchmark as well as sparse reward control tasks from the DeepMind Control Suite. Compared to state-of-the-art novelty-base
Despite the rapid progress, LLMs for sequential decision-making (i.e., LLM agents) still struggle to produce diverse outputs. This leads to insufficient exploration, convergence to sub-optimal solutions, and becoming stuck in loops. Such limitations can be problematic in environments that require active exploration to gather information and make decisions. Sampling methods such as temperature scaling introduce token-level randomness but fail to produce enough diversity at the sequence level. We analyze LLM exploration in the classic Multi-Armed Bandit (MAB) setting and the Text Adventure Learning Environment Suite (TALES). We find that current decoding strategies and prompting methods like Chain-of-Thought and Tree-of-Thought are insufficient for robust exploration. To address this, we introduce DORA Explorer (Diversity-Oriented Ranking of Actions), a training-free framework for improving exploration in LLM agents. DORA generates diverse action candidates, scores them using token log-probabilities, and selects actions using a tunable exploration parameter. DORA achieves UCB-competitive performance on MAB and consistent gains across TALES, e.g., improving Qwen2.5-7B's performance fr
Adaptive exploration methods propose ways to learn complex policies via alternating between exploration and exploitation. An important question for such methods is to determine the appropriate moment to switch between exploration and exploitation and vice versa. This is critical in domains that require the learning of long and complex sequences of actions. In this work, we present a generic adaptive exploration framework that employs uncertainty to address this important issue in a principled manner. Our framework includes previous adaptive exploration approaches as special cases. Moreover, we can incorporate in our framework any uncertainty-measuring mechanism of choice, for instance mechanisms used in intrinsic motivation or epistemic uncertainty-based exploration methods. We experimentally demonstrate that our framework gives rise to adaptive exploration strategies that outperform standard ones across several environments.
In reinforcement learning, the optimism in the face of uncertainty (OFU) is a mainstream principle for directing exploration towards less explored areas, characterized by higher uncertainty. However, in the presence of environmental stochasticity (noise), purely optimistic exploration may lead to excessive probing of high-noise areas, consequently impeding exploration efficiency. Hence, in exploring noisy environments, while optimism-driven exploration serves as a foundation, prudent attention to alleviating unnecessary over-exploration in high-noise areas becomes beneficial. In this work, we propose Optimistic Value Distribution Explorer (OVD-Explorer) to achieve a noise-aware optimistic exploration for continuous control. OVD-Explorer proposes a new measurement of the policy's exploration ability considering noise in optimistic perspectives, and leverages gradient ascent to drive exploration. Practically, OVD-Explorer can be easily integrated with continuous control RL algorithms. Extensive evaluations on the MuJoCo and GridChaos tasks demonstrate the superiority of OVD-Explorer in achieving noise-aware optimistic exploration.
Knowledge Graphs (KGs) enable the integration and representation of complex information across domains, but their semantic richness and structural complexity create substantial barriers for lay users without expertise in semantic web technologies. When encountering an unfamiliar KG, such users face a distinct orientation challenge: they do not know what questions are possible, how the knowledge is structured, or how to begin exploration. This paper identifies and theorises this phenomenon as the Initial Exploration Problem (IEP). Drawing on theories from information behaviour and human-computer interaction, including ASK, exploratory search, information foraging, and cognitive load theory, we develop a conceptual framing of the IEP characterised by three interdependent barriers: scope uncertainty, ontology opacity, and query incapacity. We argue that these barriers converge at the moment of first contact, distinguishing the IEP from related concepts that presuppose an existing starting point or information goal. Analysing KG exploration interfaces at the level of interaction primitives, we suggest that many systems rely on epistemic assumptions that do not hold at first contact. Th
Exploration remains a critical issue in deep reinforcement learning for an agent to attain high returns in unknown environments. Although the prevailing exploration Random Network Distillation (RND) algorithm has been demonstrated to be effective in numerous environments, it often needs more discriminative power in bonus allocation. This paper highlights the "bonus inconsistency" issue within RND, pinpointing its primary limitation. To address this issue, we introduce the Distributional RND (DRND), a derivative of the RND. DRND enhances the exploration process by distilling a distribution of random networks and implicitly incorporating pseudo counts to improve the precision of bonus allocation. This refinement encourages agents to engage in more extensive exploration. Our method effectively mitigates the inconsistency issue without introducing significant computational overhead. Both theoretical analysis and experimental results demonstrate the superiority of our approach over the original RND algorithm. Our method excels in challenging online exploration scenarios and effectively serves as an anti-exploration mechanism in D4RL offline tasks. Our code is publicly available at https
A well-balanced exploration-exploitation trade-off is crucial for successful acquisition functions in Bayesian optimization. However, there is a lack of quantitative measures for exploration, making it difficult to analyze and compare different acquisition functions. This work introduces two novel approaches - observation traveling salesman distance and observation entropy - to quantify the exploration characteristics of acquisition functions based on their selected observations. Using these measures, we examine the explorative nature of several well-known acquisition functions across a diverse set of black-box problems, uncover links between exploration and empirical performance, and reveal new relationships among existing acquisition functions. Beyond enabling a deeper understanding of acquisition functions, these measures also provide a foundation for guiding their design in a more principled and systematic manner.
I present diffusion models as part of a family of machine learning techniques that withhold information from a model's input and train it to guess the withheld information. I argue that diffusion's destroying approach to withholding is more flexible than typical hand-crafted information withholding techniques, providing a rich training playground that could be advantageous in some settings, notably data-scarce ones. I then address subtle issues that may arise when porting reinforcement learning techniques to the diffusion context, and wonder how such exploration problems could be addressed in more diffusion-native ways. I do not have definitive answers, but I do point my fingers in directions I deem interesting. A tutorial follows this thesis, expanding on the destroy-then-generate perspective. A novel kind of probabilistic graphical models is introduced to facilitate the tutorial's exposition.
Planetary exploration increasingly relies on autonomous robotic systems capable of perceiving, interpreting, and reconstructing their surroundings in the absence of global positioning or real-time communication with Earth. Rovers operating on planetary surfaces must navigate under sever environmental constraints, limited visual redundancy, and communication delays, making onboard spatial awareness and visual localization key components for mission success. Traditional techniques based on Structure-from-Motion (SfM) and Simultaneous Localization and Mapping (SLAM) provide geometric consistency but struggle to capture radiometric detail or to scale efficiently in unstructured, low-texture terrains typical of extraterrestrial environments. This work explores the integration of radiance field-based methods - specifically Neural Radiance Fields (NeRF) and Gaussian Splatting - into a unified, automated environment reconstruction pipeline for planetary robotics. Our system combines the Nerfstudio and COLMAP frameworks with a ROS2-compatible workflow capable of processing raw rover data directly from rosbag recordings. This approach enables the generation of dense, photorealistic, and metr
Executive Summary: The Habitable Worlds Observatory (HWO) is the first astrophysics flagship mission with a key cross-divisional astrobiology science goal of searching for signs of life on rocky planets beyond our solar system. The Living Worlds Working Group under the Science, Technology, and Architecture Review Team (START) was charged with investigating how HWO could characterize potentially habitable exoplanets orbiting stars in the solar neighborhood, search for signs of life, and interpret potential biosignatures within a false positive and false negative framework. In particular, we focused on (1) identifying biosignatures that have spectral features in the UV-Vis-NIR wavelength range and defining their measurement requirements, (2) determining additional information needed from the planet and planet system to interpret biosignatures and assess the likelihood of false positives, and (3) assembling current knowledge of likely HWO target stars and identify which properties of host stars and systems are most critical to know in advance of HWO. The Living Worlds atmospheric biosignatures science case is considered one of the key drivers in the design of the observatory. An addit
The 2023-2032 Planetary Science and Astrobiology Decadal Survey Origins, Worlds, and Life recommended that "NASA develop scientific exploration strategies, as it has for Mars, in areas of broad scientific importance, e.g., Venus... that have an increasing number of U.S. missions and international collaboration opportunities" (OWL, p.22-10). In NASA's initial responses to that Decadal Survey, the agency asserted that "...specific scientific exploration strategies should be community generated by bodies such as the Analysis Groups," thus placing the onus on the planetary community to generate and support these exploration strategies. In late 2022, the Venus Exploration Analysis Group began a project to develop a new exploration strategy for Venus, reflecting the 2021 selections of the VERITAS, DAVINCI, and EnVision missions and the sweeping comparative planetology recommendations relevant to Venus in Origins, Worlds, and Life. This is that strategy. Taking a broad look at the scientific, technological, and programmatic advances required to address the key outstanding questions that Venus poses, and predicated on VERITAS, DAVINCI, and EnVision flying as planned in the early 2030s, thi
We consider the problem of Embodied Question Answering (EQA), which refers to settings where an embodied agent such as a robot needs to actively explore an environment to gather information until it is confident about the answer to a question. In this work, we leverage the strong semantic reasoning capabilities of large vision-language models (VLMs) to efficiently explore and answer such questions. However, there are two main challenges when using VLMs in EQA: they do not have an internal memory for mapping the scene to be able to plan how to explore over time, and their confidence can be miscalibrated and can cause the robot to prematurely stop exploration or over-explore. We propose a method that first builds a semantic map of the scene based on depth information and via visual prompting of a VLM - leveraging its vast knowledge of relevant regions of the scene for exploration. Next, we use conformal prediction to calibrate the VLM's question answering confidence, allowing the robot to know when to stop exploration - leading to a more calibrated and efficient exploration strategy. To test our framework in simulation, we also contribute a new EQA dataset with diverse, realistic hum
The Exoplanet Exploration Program (ExEP) is chartered by the NASA Astrophysics Division to carry out science, research, and technology tasks that advance NASA's science goals for exoplanets. The ExEP Science Gap List is a compilation of "science gaps", defined as either: 1) The difference between knowledge needed to define requirements for specified future NASA exoplanet missions and the current state of the art, or 2) Knowledge which is needed to enhance the exoplanet science return of current and future NASA exoplanet missions. It is annually updated and input is solicited from the exoplanet community via ExoPAG. Current gaps are: 1) Spectroscopic observations of the atmospheres of small exoplanets, 2) Modeling exoplanet atmospheres, 3) Spectral signature retrieval, 4) Planetary system architectures: occurrence rates for exoplanets of all sizes, 5) Occurrence rates and uncertainties for temperate rocky planets, 6) Yield estimation for exoplanet direct imaging missions, 7) Intrinsic properties of known exoplanet host stars, 8) Mitigating stellar jitter as a limitation to sensitivity of dynamical methods to detect small temperate exoplanets and measure their masses and orbits, 9) D
Robots struggle to understand object properties like shape, material, and semantics due to limited prior knowledge, hindering manipulation in unstructured environments. In contrast, humans learn these properties through interactive multi-sensor exploration. This work proposes fusing visual and tactile observations into a unified Gaussian Process Distance Field (GPDF) representation for active perception of object properties. While primarily focusing on geometry, this approach also demonstrates potential for modeling surface properties beyond geometry. The GPDF encodes signed distance using point cloud, analytic gradient and Hessian, and surface uncertainty estimates, which are attributes that common neural network shape representation lack. By utilizing a point cloud to construct a distance function, GPDF does not need extensive pretraining on large datasets and can incorporate observations by aggregation. Starting with an initial visual shape estimate, the framework iteratively refines the geometry by integrating dense vision measurements using differentiable rendering and tactile measurements at uncertain surface regions. By quantifying multi-sensor uncertainties, it plans explor
The continuous expansion of open data platforms and research repositories has led to a fragmented dataset ecosystem, posing significant challenges for cross-source data discovery and interpretation. To address these challenges, we introduce SeDa--a unified framework for dataset discovery, semantic annotation, and multi-entity augmented navigation. SeDa integrates more than 7.6 million datasets from over 200 platforms, spanning governmental, academic, and industrial domains. The framework first performs semantic extraction and standardization to harmonize heterogeneous metadata representations. On this basis, a topic-tagging mechanism constructs an extensible tag graph that supports thematic retrieval and cross-domain association, while a provenance assurance module embedded within the annotation process continuously validates dataset sources and monitors link availability to ensure reliability and traceability. Furthermore, SeDa employs a multi-entity augmented navigation strategy that organizes datasets within a knowledge space of sites, institutions, and enterprises, enabling contextual and provenance-aware exploration beyond traditional search paradigms. Comparative experiments
Nanotechnology has emerged as a transformative force across multiple industries, enhancing materials, improving instrumentation precision, and developing intelligent systems. This review explores various nanotechnology applications, including advancements in materials science, healthcare, energy storage, environmental monitoring, and robotics. Nanomaterials, such as carbon nanotubes and graphene, offer significant improvements in fields like energy generation and medicine, while nanosensors revolutionize environmental and industrial monitoring. Micro and nano robots provide automation solutions across industries. By expanding beyond space exploration, this review highlights the far-reaching potential of nanotechnology to reshape industries through interdisciplinary collaboration and innovation.
This paper provides an empirical evaluation of recently developed exploration algorithms within the Arcade Learning Environment (ALE). We study the use of different reward bonuses that incentives exploration in reinforcement learning. We do so by fixing the learning algorithm used and focusing only on the impact of the different exploration bonuses in the agent's performance. We use Rainbow, the state-of-the-art algorithm for value-based agents, and focus on some of the bonuses proposed in the last few years. We consider the impact these algorithms have on performance within the popular game Montezuma's Revenge which has gathered a lot of interest from the exploration community, across the the set of seven games identified by Bellemare et al. (2016) as challenging for exploration, and easier games where exploration is not an issue. We find that, in our setting, recently developed bonuses do not provide significantly improved performance on Montezuma's Revenge or hard exploration games. We also find that existing bonus-based methods may negatively impact performance on games in which exploration is not an issue and may even perform worse than $ε$-greedy exploration.
The growing trends in automation, Internet of Things, big data and cloud computing technologies have led to the fourth industrial revolution (Industry 4.0), where it is possible to visualize and identify patterns and insights, which results in a better understanding of the data and can improve the manufacturing process. However, many times, the task of data exploration results difficult for manufacturing experts because they might be interested in analyzing also data that does not appear in pre-designed visualizations and therefore they must be assisted by Information Technology experts. In this paper, we present a proposal materialized in a semantic-based visual query system developed for a real Industry 4.0 scenario that allows domain experts to explore and visualize data in a friendly way. The main novelty of the system is the combined use that it makes of captured data that are semantically annotated first, and a 2D customized digital representation of a machine that is also linked with semantic descriptions. Those descriptions are expressed using terms of an ontology, where, among others, the sensors that are used to capture indicators about the performance of a machine that b
Interactive data exploration (IDE) is an effective way of comprehending big data, whose volume and complexity are beyond human abilities. The main goal of IDE is to discover user interest regions from a database through multi-rounds of user labelling. Existing IDEs adopt active-learning framework, where users iteratively discriminate or label the interestingness of selected tuples. The process of data exploration can be viewed as the process of training a classifier, which determines whether a database tuple is interesting to a user. An efficient exploration thus takes very few iterations of user labelling to reach the data region of interest. In this work, we consider the data exploration as the process of few-shot learning, where the classifier is learned with only a few training examples, or exploration iterations. To this end, we propose a learning-to-explore framework, based on meta-learning, which learns how to learn a classifier with automatically generated meta-tasks, so that the exploration process can be much shortened. Extensive experiments on real datasets show that our proposal outperforms existing explore-by-example solutions in terms of accuracy and efficiency.
We consider the problem of exploration of networks, some of whose edges are faulty. A mobile agent, situated at a starting node and unaware of which edges are faulty, has to explore the connected fault-free component of this node by visiting all of its nodes. The cost of the exploration is the number of edge traversals. For a given network and given starting node, the overhead of an exploration algorithm is the worst-case ratio (taken over all fault configurations) of its cost to the cost of an optimal algorithm which knows where faults are situated. An exploration algorithm, for a given network and given starting node, is called perfectly competitive if its overhead is the smallest among all exploration algorithms not knowing the location of faults. We design a perfectly competitive exploration algorithm for any ring, and show that, for networks modeled by hamiltonian graphs, the overhead of any DFS exploration is at most 10/9 times larger than that of a perfectly competitive algorithm. Moreover, for hamiltonian graphs of size at least 24, this overhead is less than 6% larger than that of a perfectly competitive algorithm.