Search Results for author: Mark Gluzman

Found 4 papers, 1 papers with code

Processing Network Controls via Deep Reinforcement Learning

no code implementations1 May 2022 Mark Gluzman

Policy improvement bounds play a crucial role in the theoretical justification of the APG algorithms.

reinforcement-learning Reinforcement Learning (RL)

Refined Policy Improvement Bounds for MDPs

no code implementations16 Jul 2021 J. G. Dai, Mark Gluzman

The existing bound leads to a degenerate bound when the discount factor approaches one, making the applicability of TRPO and related algorithms questionable when the discount factor is close to one.

Queueing Network Controls via Deep Reinforcement Learning

no code implementations31 Jul 2020 J. G. Dai, Mark Gluzman

A key to the successes of our PPO algorithm is the use of three variance reduction techniques in estimating the relative value function via sampling.

reinforcement-learning Reinforcement Learning (RL)

Optimizing adaptive cancer therapy: dynamic programming and evolutionary game theory

1 code implementation5 Dec 2018 Mark Gluzman, Jacob G. Scott, Alexander Vladimirsky

In particular, we optimize the total drug usage and time to recovery by solving a Hamilton-Jacobi-Bellman equation based on a mathematical model of tumor evolution.

Quantitative Methods 92C50, 49N90, 49Lxx

Cannot find the paper you are looking for? You can Submit a new open access paper.