4 papers
Reinforcement Learning for Continuous-Time Jump Markov Decision Processes with Applications to Network Dynamic Pricing
Huiling Meng, Ningyuan Chen, Xuefeng Gao
We study reinforcement learning (RL) in Continuous-Time Jump Markov Decision Processes (CTJMDPs) featuring general discrete state spaces (which need not possess a vector space stru…
Reinforcement Learning for Intensity Control: An Application to Choice-Based Network Revenue Management
Huiling Meng, Ningyuan Chen, Xuefeng Gao
Intensity control is a class of continuous-time dynamic optimization problems with many important applications in Operations Research including queueing and revenue management. In…
Design Experiments to Compare Multi-armed Bandit Algorithms
Huiling Meng, Ningyuan Chen, Xuefeng Gao
Online platforms routinely compare multi-armed bandit algorithms, such as UCB and Thompson Sampling, to select the best-performing policy. Unlike standard A/B tests for static trea…
Is Thompson Sampling Susceptible to Algorithmic Collusion?
Yi Xiong, Ningyuan Chen, Xuefeng Gao
When two players are engaged in a repeated game with unknown payoff matrices, they may use single-agent multi-armed bandit algorithms to choose the actions independent of each othe…