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

← all fields·3 papers on “reinforcement learning” in Statistical ML · 1 week

Active Inference as a Convex Markov Decision Processcs.LG

AIF reformulated as convex MDP for adaptive behavior.

problem Adaptive behavior and policy optimization.

method Formulating AIF as convex MDP, deriving mirror descent algorithm.

result EFE minimization in AIF is equivalent to reward maximization in latent MDP, with epistemic component.

Active Inference Markov Decision Process Mirror Descent Reinforcement Learning Epistemic Value

2026-07-22abs ↗pdf ↗

Asymptotically Optimal Regret for Reinforcement Learning without Horizon Dependencecs.LG

New algorithm achieves asymptotically optimal regret without horizon dependence.

problem Horizon-free regret minimization for reinforcement learning.

method Proposes a new algorithm and proves a regret upper bound.

result Regret upper bound of \(\tilde O(\sqrt{SAK} + S^8A^3)\) with failure probability \(\delta\).

Reinforcement Learning Horizon-Free Regret Minimization Markov Decision Processes Monotonicity

2026-07-22abs ↗pdf ↗

Non-Asymptotic Best Policy Identification Guarantees in Online Reinforcement Learningstat.ML

Study non-asymptotic BPI guarantees for online RL.

problem Identify optimal policy in MDP with high confidence.

method Non-asymptotic sample complexity guarantees for NaS algorithm.

result Sample complexity depends on MDP connectivity and curvature.

Reinforcement Learning Best Policy Identification Online Learning Markov Decision Process Non-asymptotic Analysis

2026-07-19abs ↗pdf ↗