Related papers: Dynamic Exploration-Exploitation Trade-Off in Acti…

Active search formalizes a specialized active learning setting where the goal is to collect members of a rare, valuable class. The state-of-the-art algorithm approximates the optimal Bayesian policy in a budget-aware manner, and has been…

Recent advances in machine learning have led to increased deployment of black-box classifiers across a wide variety of applications. In many such situations there is a critical need to both reliably assess the performance of these…

Solving real-life sequential decision making problems under partial observability involves an exploration-exploitation problem. To be successful, an agent needs to efficiently gather valuable information about the state of the world for…

Although exploratory behaviors are ubiquitous in the animal kingdom, their computational underpinnings are still largely unknown. Behavioral Psychology has identified learning as a primary drive underlying many exploratory behaviors.…

This work pushes the boundaries of learning-based methods in autonomous robot exploration in terms of environmental scale and exploration efficiency. We present HEADER, an attention-based reinforcement learning approach with hierarchical…

We propose a novel holistic approach for safe autonomous exploration and map building based on constrained Bayesian optimisation. This method finds optimal continuous paths instead of discrete sensing locations that inherently satisfy…

With the rising complexity of numerous novel applications that serve our modern society comes the strong need to design efficient computing platforms. Designing efficient hardware is, however, a complex multi-objective problem that deals…

Bayesian optimization (BO) is an attractive machine learning framework for performing sample-efficient global optimization of black-box functions. The optimization process is guided by an acquisition function that selects points to acquire…

Active inference (AIF) unifies exploration and exploitation by minimizing the Expected Free Energy (EFE), balancing epistemic value (information gain) and pragmatic value (task performance) through a curiosity coefficient. Yet it has been…

Active learning aims to select a small subset of data for annotation such that a classifier learned on the data is highly accurate. This is usually done using heuristic selection methods, however the effectiveness of such methods is limited…

Online model-free reinforcement learning (RL) methods with continuous actions are playing a prominent role when dealing with real-world applications such as Robotics. However, when confronted to non-stationary environments, these methods…

The inherent trade-off in on-line learning is between exploration and exploitation. A good balance between these two (conflicting) goals can achieve a better long-term performance. Can we define an optimal balance? We propose to study this…

Numerous heuristics and advanced approaches have been proposed for exploration in different settings for deep reinforcement learning. Noise-based exploration generally fares well with dense-shaped rewards and bonus-based exploration with…

To determine an optimal plan for complex tasks, one often deals with dynamic and hierarchical relationships between several entities. Traditionally, such problems are tackled with optimal control, which relies on the optimization of cost…

Robots with increasing autonomy progress our space exploration capabilities, particularly for in-situ exploration and sampling to stand in for human explorers. Currently, humans drive robots to meet scientific objectives, but depending on…

Successful engineering requires environmentally adapted procedural and architectural approaches. While dealing with complicated issues has become an engineering standard mastering uncertainties in complex environment is still a major issue.…

While adaptive experimental design has outgrown one-dimensional, staircase-based adaptations, most cognitive experiments still control a single factor and summarize performance with a scalar. We show a validation of a Bayesian, two-axis,…

This paper presents an information-theoretic framework for unifying active learning problems: level set estimation (LSE), Bayesian optimization (BO), and their generalized variant. We first introduce a novel active learning criterion that…

Bayesian model comparison (BMC) offers a principled approach for assessing the relative merits of competing computational models and propagating uncertainty into model selection decisions. However, BMC is often intractable for the popular…

Machine learning interatomic force fields are promising for combining high computational efficiency and accuracy in modeling quantum interactions and simulating atomistic dynamics. Active learning methods have been recently developed to…