Research map / Bandits and online learning / Multi-armed bandits
Finite-Time Analysis of Whittle Index based Q-Learning for Restless Multi-Armed Bandits with Neural Network Function Approximation
GUOJUN XIONG, Jian Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| update Whittle index of every state at each step (Neural-Q-Whittle) instead of only the visited state (Q-Whittle) | Neural-Q-Whittle · circulant 4-state RMAB | convergence speed to true Whittle indices | Improved |
| compare Neural-Q-Whittle against WIQL and QWIC | Neural-Q-Whittle · circulant 4-state RMAB | convergence to true Whittle indices | Improved |
| replace linear function approximation (Q-Whittle-LFA) with a two-layer neural network | Q-Whittle · circulant 4-state RMAB | convergence to true Whittle indices | No clear effect |
| increase hidden-layer width m of the neural network | Neural-Q-Whittle · circulant 4-state RMAB | constant c0 in Assumption | Improved |
| run more iterations k | Neural-Q-Whittle · circulant 4-state RMAB, state 4 | Lyapunov function E[M] | Improved |
Closest papers by meaning
- GINO-Q: Learning an Asymptotically Optimal Index Policy for Restless Multi-armed Bandits (AAAI 2026 · similarity 0.89)
- Global Rewards in Restless Multi-Armed Bandits (NeurIPS 2024 · similarity 0.85)
- Achieving $\tilde{\mathcal{O}}(1/N)$ Optimality Gap in Restless Bandits through Gaussian Approximation (NeurIPS 2025 · similarity 0.84)
- The Bandit Whisperer: Communication Learning for Restless Bandits (AAAI 2025 · similarity 0.83)
- Long-Horizon Q-Learning: Accurate Value Learning via n-Step Inequalities (NeurIPS 2026 · similarity 0.83)
- Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback (ICML 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
