Introduces pessimistic and opportunistic policies for offline dynamic pricing under no price coverage via partial identification from demand monotonicity, with finite-sample regret bounds that recover standard rates when coverage exists.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2024 2verdicts
UNVERDICTED 2representative citing papers
A continuous-time RL framework for intensity control in choice-based network revenue management outperforms discretization-based methods while scaling to large problems.
citing papers explorer
-
A Tale of Two Cities: Pessimism and Opportunism in Offline Dynamic Pricing
Introduces pessimistic and opportunistic policies for offline dynamic pricing under no price coverage via partial identification from demand monotonicity, with finite-sample regret bounds that recover standard rates when coverage exists.
-
Reinforcement Learning for Intensity Control: An Application to Choice-Based Network Revenue Management
A continuous-time RL framework for intensity control in choice-based network revenue management outperforms discretization-based methods while scaling to large problems.