A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Active sampling improves design space exploration for analog circuits.
AceIRL learns expert reward from active exploration.
Active inference enhances RL by balancing exploration and exploitation.
Paper develops a dynamic Bayesian approach for active learning that optimizes exploration-exploitation balance.
Active learning method improves AI performance by balancing exploration and exploitation.
We introduce the active exploration problem in Markov decision processes (MDPs). Each state of the MDP is characterized by a random value and the learner should gather samples to estimate the mean value of each state as accurately as possible. Similarly to active exploration in multi-armed bandit (MAB), states may have…
Efficient exploration is an unsolved problem in Reinforcement Learning which is usually addressed by reactively rewarding the agent for fortuitously encountering novel situations. This paper introduces an efficient active exploration algorithm, Model-Based Active eXploration (MAX), which uses an ensemble of forward mod…
SAMBA improves safe reinforcement learning with active exploration metrics.
An artificial neuron is modelled as a weighted summation followed by an activation function which determines its output. A wide variety of activation functions such as rectified linear units (ReLU), leaky-ReLU, Swish, MISH, etc. have been explored in the literature. In this short paper, we explore what happens when the…
In graph-based active learning, algorithms based on expected error minimization (EEM) have been popular and yield good empirical performance. The exact computation of EEM optimally balances exploration and exploitation. In practice, however, EEM-based algorithms employ various approximations due to the computational ha…
New algorithm improves graph-based active learning by identifying unexplored regions.
Developing active inference agents for edge devices with limited resources.
A new MARL framework for community-based cooperation with transfer and active exploration.
A new active learning method for Gaussian process models.
MAPS and MAPS-SE learn from multiple suboptimal experts to improve policies efficiently.
This work designs an active world model learning system with progress-based curiosity.
We present an active learning architecture that allows a robot to actively learn which data collection strategy is most efficient for acquiring motor skills to achieve multiple outcomes, and generalise over its experience to achieve new outcomes. The robot explores its environment both via interactive learning and goal…
A new criterion for deep active learning selects minimal labeled data points.
We present a new algorithm based on an gradient ascent for a general Active Exploration bandit problem in the fixed confidence setting. This problem encompasses several well studied problems such that the Best Arm Identification or Thresholding Bandits. It consists of a new sampling rule based on an online lazy mirror …
A new framework scales active search for large datasets.
DiAL uses Bayesian Dirichlet random fields for active learning with sparse labels.
We present the Variational Adaptive Newton (VAN) method which is a black-box optimization method especially suitable for explorative-learning tasks such as active learning and reinforcement learning. Similar to Bayesian methods, VAN estimates a distribution that can be used for exploration, but requires computations th…
Agent uses message passing to optimize robot navigation, balancing exploration and exploitation.
A new AI framework optimizes expert labeling of unlabeled data.
Improves active learning efficiency by warping input space based on observed outputs.
Active learning has long been a topic of study in machine learning. However, as increasingly complex and opaque models have become standard practice, the process of active learning, too, has become more opaque. There has been little investigation into interpreting what specific trends and patterns an active learning st…
Active Reinforcement Learning (ARL) is a twist on RL where the agent observes reward information only if it pays a cost. This subtle change makes exploration substantially more challenging. Powerful principles in RL like optimism, Thompson sampling, and random exploration do not help with ARL. We relate ARL in tabular …
New method avoids failures in physics-constrained systems using active learning.
Model based predictions of future trajectories of a dynamical system often suffer from inaccuracies, forcing model based control algorithms to re-plan often, thus being computationally expensive, suboptimal and not reliable. In this work, we propose a model agnostic method for estimating the uncertainty of a model?s pr…
New RL agent learns sparse rewards efficiently.
We explore the efficacy of using a novel activation function in Artificial Neural Networks (ANN) in characterizing exoplanets into different classes. We call this Saha-Bora Activation Function (SBAF) as the motivation is derived from long standing understanding of using advanced calculus in modeling habitability score …
Activation functions influence behavior and performance of DNNs. Nonlinear activation functions, like Rectified Linear Units (ReLU), Exponential Linear Units (ELU) and Scaled Exponential Linear Units (SELU), outperform the linear counterparts. However, selecting an appropriate activation function is a challenging probl…
Efficiently identifies good policies by choosing contexts for human feedback.
Many activation functions have been proposed in the past, but selecting an adequate one requires trial and error. We propose a new methodology of designing activation functions within a neural network at each layer. We call this technique an "activation ensemble" because it allows the use of multiple activation functio…
Study shows sample noise impacts active learning performance.
Active learning aims to obtain a classifier of high accuracy by using fewer label requests in comparison to passive learning by selecting effective queries. Many active learning methods have been developed in the past two decades, which sample queries based on informativeness or representativeness of unlabeled data poi…
New framework improves fairness in small data settings.
Robots learn actions and language through curiosity-driven self-exploration.
New model considers varying costs in learning, outperforming existing methods.
Active learning from demonstration allows a robot to query a human for specific types of input to achieve efficient learning. Existing work has explored a variety of active query strategies; however, to our knowledge, none of these strategies directly minimize the performance risk of the policy the robot is learning. U…
Active learning improves SR by proposing experiments in data-limited settings.
We propose a simple extension to the ReLU-family of activation functions that allows them to shift the mean activation across a layer towards zero. Combined with proper weight initialization, this alleviates the need for normalization layers. We explore the training of deep vanilla recurrent neural networks (RNNs) with…
Bayesian search optimizes exploration of feasible solutions under expensive constraints.
DiffATD efficiently discovers targets in partially observable environments using diffusion dynamics.
The study examines if ReLU activation function is optimal for modularity in neural networks.
Evolutionary algorithms improve neural network performance by discovering better activation functions.
When approximating a black-box function, sampling with active learning focussing on regions with non-linear responses tends to improve accuracy. We present the FLOLA-Voronoi method introduced previously for deterministic responses, and theoretically derive the impact of output uncertainty. The algorithm automatically p…
RL policy tracks dynamic targets in partially known environments robustly.