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.

168,657 papers · 148 categories

Trend · papers per month

1223 · Oct 202419922001200920172026
12 results for RMAB

Proposes a fair RMAB framework ensuring equal exposure to arms.

problem Fairness in RMABs where arms are not equally exposed.
method Defines merit of each arm based on stationary reward distribution and ensures equal exposure in proportion to merit.
result Achieves sublinear fairness regret of O(TlnT)O(\sqrt{T\ln T}) in single pull case.

New RL algorithm tackles adversarial RMAB with unknown transitions and bandit feedback.

problem Learning in episodic RMAB with unknown transition functions and adversarial rewards.
method Developed a novel RL algorithm with a biased reward estimator and an index policy.
result Achieved ildeO(HT) ilde{\mathcal{O}}(H\sqrt{T}) regret bound for adversarial RMAB.

New approach tackles non-Markovian behavior in maternal health programs.

problem Improving adherence and engagement in maternal and child healthcare programs.
method Extending RMABs to non-Markovian settings, using time-series forecasting and TARI policy.
result Significant increase in engagement and content listened compared to existing methods.

New model predicts optimal control for restless bandit problems.

problem Optimizing control in restless bandit problems with minimal assumptions.
method Model Predictive Control with rolling horizon linear programming.
result Sub-optimality gap of O(1/√N) under general conditions, and exp(-Ω(N)) under local-stability condition.

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.

New algorithm optimizes resource allocation in non-stationary networks.

problem Optimal resource allocation in non-stationary RMABs is computationally hard.
method Sliding-Window Online Whittle (SW-Whittle) policy for non-stationary transition kernels.
result Sub-linear dynamic regret achieved with unknown variation budget.

ContextWIN uses neural networks and reinforcement learning to optimize decisions in dynamic environments.

problem Optimizing decisions in dynamic, context-aware environments like recommendation systems.
method Integrates a mixture of experts within a reinforcement learning framework to compute context-specific weights for decision-making.
result Enhanced efficiency and accuracy in Whittle index computation for each arm in RMABs.

New algorithm optimizes decision-making for complex systems with varying parameters.

problem Optimizing decisions in systems with varying parameters and heterogeneous restlessness.
method Model Predictive Control (MPC) approach with randomized rounding for heterogeneous RMABs.
result Achieves an O(logN1/N)O(\log N\sqrt{1/N}) optimality gap in infinite time average reward problems.