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.

168,932 papers · 148 categories

Trend · papers per month

count % of corpus

1 result for “UCRL-V”

Near-optimal Optimistic Reinforcement Learning using Empirical Bernstein Inequalitiescs.LG

UCRL-V algorithm achieves optimal regret in unknown MDPs.

problem Optimizing reinforcement learning in unknown finite Markov decision processes.

method Empirical Bernstein inequalities for variance-based confidence intervals.

result Achieves optimal regret

ilde{\mathcal{O}}(\sqrt{DSAT})

up to logarithmic factors.

reinforcement learning Markov decision process UCRL-V empirical Bernstein inequalities optimal regret

2019-05-27abs ↗pdf ↗