60 citations · 94 across the 5 of their papers we have counts for
5 papers
Refined Policy Improvement Bounds for MDPs
J. G. Dai, Mark Gluzman
The policy improvement bound on the difference of the discounted returns plays a crucial role in the theoretical justification of the trust-region policy optimization (TRPO) algori…
High order steady-state diffusion approximations
Anton Braverman, J. G. Dai, Xiao Fang
We derive and analyze new diffusion approximations of stationary distributions of Markov chains that are based on second- and higher-order terms in the expansion of the Markov chai…
Scalable Deep Reinforcement Learning for Ride-Hailing
Jiekun Feng, Mark Gluzman, J. G. Dai
Ride-hailing services, such as Didi Chuxing, Lyft, and Uber, arrange thousands of cars to meet ride requests throughout the day. We consider a Markov decision process (MDP) model o…
Queueing Network Controls via Deep Reinforcement Learning
J. G. Dai, Mark Gluzman
Novel advanced policy gradient (APG) methods, such as Trust Region policy optimization and Proximal policy optimization (PPO), have become the dominant reinforcement learning algor…
Empty-car routing in ridesharing systems
Anton Braverman, J. G. Dai, Xin Liu +1
This paper considers a closed queueing network model of ridesharing systems such as Didi Chuxing, Lyft, and Uber. We focus on empty-car routing, a mechanism by which we control car…