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.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “self-exploration”

Curiosity-Driven Development of Action and Language in Robots Through Self-Explorationstat.ML

Robots learn actions and language through curiosity-driven self-exploration.

problem Efficient development of actions and language in infants and robots.

method Curiosity-driven self-exploration using Q-learning to amortize active inference.

result Curiosity-driven exploration enables faster learning and compositional generalization.

robotics language learning curiosity self-exploration Q-learning

2025-10-06abs ↗pdf ↗

Active choice of teachers, learning strategies and goals for a socially guided intrinsic motivation learnercs.LG

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…

2018-04-18abs ↗pdf ↗

Avoiding

\mathbf{exp(R_{max})}

scaling in RLHF through Preference-based Explorationcs.LG

Improves RLHF sample efficiency by scaling reward complexity polynomially.

problem Exponential sample complexity in RLHF algorithms for skewed preferences.

method SE-POPO, an online RLHF algorithm that achieves polynomial sample complexity.

result SE-POPO outperforms existing algorithms in sample efficiency.

Reinforcement Learning Human Feedback Sample Efficiency Polynomial Complexity Skewed Preferences

2025-02-02abs ↗pdf ↗

Exploration-exploitation trade-off for continuous-time episodic reinforcement learning with linear-convex modelscs.LG

New framework for RL with linear-convex models reduces performance gap.

problem Continuous-time episodic reinforcement learning with unknown coefficients and convex objectives.

method Probabilistic framework and phase-based learning algorithm for optimal exploration-exploitation trade-off.

result Sublinear regrets achieved, matching best possible results in literature.

reinforcement learning episodic continuous-time linear-convex performance gap

2021-12-19abs ↗pdf ↗

AutoFS: Automated Feature Selection via Diversity-aware Interactive Reinforcement Learningcs.LG

AutoFS combines trainers to improve feature selection efficiency and effectiveness.

problem Balancing feature selection efficiency and effectiveness.

method Interactive Reinforced Feature Selection (IRFS) framework with diverse trainers.

result Improved feature selection efficiency and effectiveness compared to existing methods.

feature selection reinforcement learning interactive learning diversity machine learning

2020-08-27abs ↗pdf ↗