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.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

10 results for “multi-action”

Offline Multi-Action Policy Learning: Generalization and Optimizationstat.ML

Paper tackles multi-action policy learning from observational data.

problem Learning policies from observational data with multiple actions.

method Semi-parametric inference theory and algorithmic approaches.

result Achieves asymptotically minimax-optimal regret for multi-action policy learning.

policy learning observational data multi-action semi-parametric inference minimax-optimal

2018-10-10abs ↗pdf ↗

Neural Index Policies for Restless Multi-Action Bandits with Heterogeneous Budgetscs.LG

Neural Index Policy for multi-action bandits with heterogeneous budgets.

problem Real-world settings often involve multiple interventions with heterogeneous costs and constraints, breaking classical assumptions.

method Introduces a Neural Index Policy (NIP) that learns to assign budget-aware indices to arm-action pairs using a neural network and differentiable knapsack layer.

result Empirically achieves near-optimal performance while strictly enforcing heterogeneous budgets and scaling to hundreds of arms.

Neural Index Policy Restless Multi-Action Bandits Heterogeneous Budgets Entropy-regularized Optimal Transport Differentiable Knapsack Layer

2025-10-24abs ↗pdf ↗

Optimal Policy Learning with Observational Data in Multi-Action Scenarios: Estimation, Risk Preference, and Potential Failuresstat.ML

Paper tackles optimal policy learning with observational data in multi-action scenarios.

problem Optimal policy learning in multi-action settings with observational data.

method Review of estimation approaches, analysis of risk preference, discussion of potential failures.

result Average regret of a policy with multi-valued treatment is contingent on the decision-maker's attitude towards risk.

policy learning observational data multi-action scenarios risk preference potential failures

2024-03-29abs ↗pdf ↗

Lower Bounds for Policy Iteration on Multi-action MDPscs.LG

Lower bounds for PI on multi-action MDPs are established, showing complexity grows with action count.

problem Establishing the minimum number of iterations for PI to converge on MDPs with multiple actions.

method Developed lower bounds for a specific PI variant on multi-action MDPs, scaling with action count.

result A particular PI variant can take

Ω(k^{n/2})

iterations to terminate, scaling with action count.

Policy Iteration Markov Decision Processes Multi-action MDPs Lower Bounds Complexity Analysis

2020-09-16abs ↗pdf ↗

Reinforcement Learning for Finite-Horizon Restless Multi-Armed Multi-Action Banditscs.LG

Optimal policy for multi-armed multi-action bandits with unknown parameters.

problem Optimal sequential action selection for multi-armed multi-action bandits with unknown parameters.

method Occupancy-Measured-Reward Index Policy (OMRIP) and R(MA)^2B-UCB algorithm.

result Asymptotically optimal policy with sub-linear regret and low computational complexity.

Reinforcement Learning Bandit Problems Multi-Armed Bandits Multi-Action Index Policy

2021-09-20abs ↗pdf ↗

Superhedging duality for multi-action options under model uncertainty with information delayq-fin.MF

Study proves duality in exotic option pricing under uncertain model and delayed information.

problem Pricing and hedging of multi-action exotic options under nondominated model uncertainty and delayed information.

method Reformulated superhedging problem as a European option problem, proving duality results.

result Superhedging price equals model-based price with future look-up power.

exotic options superhedging model uncertainty information delay duality

2021-11-29abs ↗pdf ↗

Imitation Learning with Concurrent Actions in 3D Gamescs.AI

In this work we describe a novel deep reinforcement learning architecture that allows multiple actions to be selected at every time-step in an efficient manner. Multi-action policies allow complex behaviours to be learnt that would otherwise be hard to achieve when using single action selection techniques. We use both …

2018-03-14abs ↗pdf ↗

ARL-Based Multi-Action Market Making with Hawkes Processes and Variable Volatilityq-fin.TR

ARL and Hawkes processes improve market-making strategies with variable volatility.

problem Enhancing market-making strategies to adapt to varying volatility levels and self-exciting behaviors.

method Integrates ARL, Hawkes processes, and variable volatility levels; shifts from Poisson to Hawkes process.

result 4-action MM trained in low-volatility environment adapts to high-volatility conditions, providing stable performance.

market-making ARL Hawkes processes variable volatility self-exciting

2025-08-07abs ↗pdf ↗

More Efficient Policy Learning via Optimal Retargetingstat.ML

Retargeting improves policy learning from observational data.

problem Lack of overlap in data for different actions leads to poor policy performance.

method Optimal retargeting to induce little to no bias at the population level.

result Retargeting significantly improves policy learning procedures applied to observational data.

policy learning retargeting observational data bias reduction asymptotic efficient estimation

2019-06-20abs ↗pdf ↗

Policy Learning with Observational Data: The Case of Hepatitis C Treatment for HIV/HCV Co-Infected Patientsstat.AP

Paper derives policy rules from observational data for hepatitis C treatment.

problem Improving treatment guidelines for HIV/HCV co-infected patients.

method Weighted K-means algorithm for estimating CATEs, decision tree implementation.

result Identifies a subgroup with high spontaneous HCV clearance rate.

policy learning observational data HIV/HCV co-infected treatment guidelines CATEs

2026-05-15abs ↗pdf ↗