Research
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.

168,742 papers · 148 categories

Trend · papers per month

count% of corpus
1122 · Feb 202019922001200920172026
3 results for “search-control”
Frequency-based Search-control in Dynacs.LG

A new search-control strategy improves Dyna's efficiency.

problem Improving sample efficiency in model-based reinforcement learning.
method Proposes a novel search-control strategy by sampling high frequency regions of the value function.
result Empirically shows that high frequency regions require more samples to approximate, suggesting a better search-control strategy.
reinforcement learningmodel-basedsample efficiencyDynasearch-control
2020-02-14abs ↗pdf ↗
Hill Climbing on Value Estimates for Search-control in Dynacs.LG

Dyna is an architecture for model-based reinforcement learning (RL), where simulated experience from a model is used to update policies or value functions. A key component of Dyna is search-control, the mechanism to generate the state and action from which the agent queries the model, which remains largely unexplored. …

2019-06-18abs ↗pdf ↗
Efficient Rollout Strategies for Bayesian Optimizationcs.LG

Efficiently reduces computational burden of rollout acquisition functions in Bayesian optimization.

problem Expensive computation of rollout acquisition functions in Bayesian optimization.
method Combines quasi-Monte Carlo, common random numbers, and control variates to reduce computational burden. Formulates a policy-search approach to eliminate the need to optimize the rollout acquisition function.
result Significant reduction in computational burden of rollout acquisition functions.
Bayesian optimizationrolloutacquisition functionMonte Carlopolicy-search
2020-02-24abs ↗pdf ↗