ADRL, a duality-based adversarial reinforcement learning algorithm, produces empirically tight lower and upper bounds for high-dimensional stochastic control; in a 10-asset trade execution problem the reported gap is 1.85% to 2.86%.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Adversarial Reinforcement Learning: A Duality-Based Approach To Solving Optimal Control Problems
ADRL, a duality-based adversarial reinforcement learning algorithm, produces empirically tight lower and upper bounds for high-dimensional stochastic control; in a 10-asset trade execution problem the reported gap is 1.85% to 2.86%.