On-device research index

arXiv research

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.

169,341 papers · 148 categories

Trend · papers per month

count % of corpus

9 results for “Goal-Driven”

Goal-driven Bayesian Optimal Experimental Design for Robust Decision-Making Under Model Uncertaintycs.LG

GoBOED optimizes experiments for specific decision-making objectives, improving downstream outcomes.

problem Reducing parameter uncertainty does not always improve decision-making in critical settings.

method Combines variational posterior surrogate and differentiable convex decision layer for gradient-based design optimization.

result GoBOED identifies designs that better align with specific decision objectives and reveals wider optimal design windows.

Bayesian optimal experimental design goal-driven optimization decision-making model uncertainty parameter uncertainty

2026-05-25abs ↗pdf ↗

On the Complexity of Exploration in Goal-Driven Navigationcs.LG

This paper explores how hierarchical agent policies affect exploration in goal-driven navigation environments.

problem Understanding how hierarchical agent policies influence exploration in goal-driven navigation.

method Design of EscapeRoom environments, measuring complexity with hitting times of dependency graphs, evaluating PPO and hierarchical PPO.

result Analytically estimated hitting time in goal dependency graphs is a metric of environment complexity and hierarchical approaches are necessary for complex environments.

exploration hierarchical policies goal-driven navigation hitting times dependency graphs

2018-11-16abs ↗pdf ↗

Ants, robots, humans: a self-organizing, complex systems modeling approachq-fin.GN

New modeling approach for self-organizing complex systems.

problem Identifying general principles of self-organizing complex systems.

method Self-deploying system structure and activities for goal-driven agents.

result Self-organization emerges from rational activity algorithm based on goals dependency network.

self-organization agent-based modeling complex systems rational activity goals dependency

2020-09-21abs ↗pdf ↗

Emergence of functional and structural properties of the head direction system by optimization of recurrent neural networksq-bio.NC

RNNs trained on head direction task mimic brain's compass and shifter neurons.

problem Modeling brain's head direction system using neural networks.

method Optimized recurrent neural networks trained on angular velocity integration.

result RNNs naturally emerge with compass and shifter neuron-like properties.

head direction neural networks compass neurons shifter neurons angular velocity

2019-12-21abs ↗pdf ↗

Don't Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weightscs.LG

BetaDataWeighter learns weights for unlabelled data to improve self-supervised learning accuracy.

problem Improving unsupervised representations with domain shift between unlabelled and target data.

method Learning Bayesian instance weights for unlabelled data to prioritize useful instances.

result BetaDataWeighter achieves highest average accuracy and prunes up to 78% of images without significant loss in accuracy.

self-supervised learning instance weighting unsupervised representation domain adaptation Bayesian weights

2020-06-22abs ↗pdf ↗

Many-Goals Reinforcement Learningcs.LG

The paper explores updating multiple goals in reinforcement learning with neural networks.

problem Training agents to achieve mastery in complex, non-tabular domains.

method Three extensions of Kaelbling's all-goals updating approach using deep neural networks.

result Many-goals updating can be used to pre-train networks and improve learning on a single task.

Reinforcement Learning Deep Learning Goal-Driven Mastery Neural Networks

2018-06-22abs ↗pdf ↗

Learning to Perform Physics Experiments via Deep Reinforcement Learningstat.ML

AI learns to perform experiments on objects to discover their properties.

problem Teaching AI to perform scientific experiments and infer physical properties.

method Deep reinforcement learning in a simulated environment.

result AI can learn to perform experiments to discover hidden physical properties.

deep reinforcement learning scientific intuition physical properties reinforcement learning experiments

2016-11-06abs ↗pdf ↗

Towards Deep Conversational Recommendationscs.LG

This paper collects a large dataset for conversational recommendation research.

problem Creating dialogue systems for conversational recommendation.

method Collects a large dataset (ReDial) and explores neural architectures, mechanisms, and methods for conversational recommendation systems.

result Demonstrates the utility of the collected dataset for systematic probing of model sub-components in conversational recommendation.

conversational recommendation neural networks dialogue systems movie recommendations large-scale dataset

2018-12-18abs ↗pdf ↗

Active Learning and Bayesian Optimization: a Unified Perspective to Learn with a Goalcs.LG

Unified perspective unites Bayesian optimization and active learning for efficient goal-oriented optimization.

problem Efficiently optimize expensive engineering and scientific problems with limited data.

method Unified framework linking Bayesian infill criteria and active learning criteria.

result Unified approach formalizes Bayesian infill criteria and active learning criteria.

Bayesian optimization active learning goal-oriented optimization adaptive sampling infill criteria

2023-03-02abs ↗pdf ↗