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

4 results for “action-influence”

Success Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Successcs.AI

Success conditioning optimizes policies by imitating successful trajectories, solving a trust-region optimization problem.

problem Improving policies through random actions that lead to desired outcomes.

method Success conditioning, which involves collecting and updating policies based on successful trajectories.

result Success conditioning solves a trust-region optimization problem, maximizing policy improvement with a

χ^2

divergence constraint.

success conditioning policy improvement optimization trust-region action-influence

2026-01-26abs ↗pdf ↗

Generator-Mediated Bandits: Thompson Sampling for GenAI-Powered Adaptive Interventionsstat.ML

GAMBITTS uses GenAI for adaptive interventions, improving decision-making.

problem Adaptive interventions with GenAI-generated content.

method Generator-mediated bandit-Thompson sampling (GAMBITTS).

result GAMBITTS outperforms standard bandit methods in mobile health interventions.

GenAI Thompson Sampling Adaptive Interventions Mobile Health Bandit Problems

2025-05-22abs ↗pdf ↗

Learning a functional control for high-frequency financemath.OC

Deep neural network learns optimal trading controls for high-frequency finance.

problem Optimal trading on high-frequency data with market impact and limited data.

method Deep neural network, Monte-Carlo initialization, transfer learning, explainable controls.

result Neural network learns optimal controls for trader preferences.

high-frequency finance deep learning optimal trading market impact explainable controls

2020-06-17abs ↗pdf ↗

Policy Optimization in Hybrid Discrete-Continuous Action Spaces via Mixed Gradientscs.LG

Hybrid Policy Optimization tackles reinforcement learning in hybrid spaces, improving performance over PPO.

problem Credit assignment issues and biased gradients in hybrid discrete-continuous action spaces.

method Mixed gradient estimator combining pathwise and score-function gradients, reformulating problems in hybrid form.

result HPO substantially outperforms PPO on inventory control and switched systems, with performance gaps increasing with continuous action dimension.

reinforcement learning hybrid spaces policy optimization credit assignment mixed gradients

2026-05-14abs ↗pdf ↗