polynomial scaling
- Geometry Meets Incentives: Sample-Efficient Incentivized Exploration with Linear Contexts
- Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation
- Restricted Spectral Gap Decomposition for Simulated Tempering Targeting Mixture Distributions
- Stochastic Shortest Path with Sparse Adversarial Costs
- Structure Matters: Dynamic Policy Gradient