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 “blackjack”

Variations on the Reinforcement Learning performance of Blackjackcs.AI

Study on blackjack reinforcement learning performance with varying deck sizes.

problem Understanding reinforcement learning in a stochastic environment like blackjack.

method q-learning algorithm applied to optimal play in a blackjack simulator.

result Rate of learning convergence of q-learning algorithm varies with deck size.

reinforcement learning blackjack q-learning environment variations deck size

2023-08-09abs ↗pdf ↗

Optimization and Regularization Under Arbitrary Objectivesstat.ML

The study examines MCMC methods for arbitrary objectives and finds likelihood sharpness impacts performance and regularization.

problem Limitations of MCMC methods for arbitrary objective functions.

method Two-block MCMC framework with Metropolis-Hastings and Gibbs sampling, exploring likelihood curvature and sharpness.

result Likelihood sharpness governs in-sample performance and regularization inferred by training data.

MCMC arbitrary objective likelihood curvature sharpness reinforcement learning

2025-11-24abs ↗pdf ↗

Q-learning with online random forestsstat.ML

Online random forests improve Q-learning performance in specific gym environments.

problem Improving Q-learning performance in reinforcement learning tasks.

method Proposed online random forests as Q-function approximators and growing them as learning progresses.

result Improved performance over state-of-the-art Deep Q-Networks in specific gym environments.

Q-learning reinforcement learning random forests online learning Deep Q-Networks

2022-04-07abs ↗pdf ↗

Reinforcement Learning with Quantum Variational Circuitsquant-ph

Quantum variational circuits improve reinforcement learning efficiency.

problem Improving reinforcement learning algorithms using quantum computing.

method Investigation of quantum variational circuits for DQN and Double DQN, encoding classical data for quantum circuits.

result Quantum variational circuits can solve reinforcement learning tasks with a smaller parameter space.

reinforcement learning quantum computing variational circuits deep learning superposition

2020-08-15abs ↗pdf ↗

Exploratory Gradient Boosting for Reinforcement Learning in Complex Domainscs.AI

High-dimensional observations and complex real-world dynamics present major challenges in reinforcement learning for both function approximation and exploration. We address both of these challenges with two complementary techniques: First, we develop a gradient-boosting style, non-parametric function approximator for l…

2016-03-14abs ↗pdf ↗